Develop tools and systems that apply ML to real applications on real data and try to deal with attacks and explain the decisions of AI powered decision making. In addition, the seminar will discuss methods to make these tools more efficient and more accessible.

The class provides insights about:

• Multi-modal data fusion, knowledge graphs, modeling context and situation awareness, user profiling, and matching interests with streaming data ( sensors, text, tweets, video, news articles, emails, phone calls), pattern recognition, data mining, intelligent query processing. Machine learning models to connect user's needs with data based on situation and context awareness.
• Privacy-enabling frameworks for situational-aware systems. Representing networks and knowledge graphs using graph databases, graph analytics for enhancing search.
• Machine learning in data cleaning, video data understanding, and data mining and identifying objects and events. Modeling user queries to build knowledge graphs to target data to users. AutoML and self-supervised learning: Deep learning to accelerate the labeling of data and carefully tune hyper-parameters. Learn automatically and learn on unlabeled data to make machine learning accurate and efficient. Labeling and learning with incomplete or limited data.
• Attacks on ML models, training data, and streaming data. Preserving privacy and security by monitoring attacks, mitigating attacks, dealing with changing behavior of adversary, collaborative attacks, predicting attacks, and intent. Deep learning-based Programming Language Processing for Detecting Evasive Cyber-attacks, Trusted Classification under Poisoning attacks using Semantic Factors. Bias and Fairness in ML, what fairness means, causes that introduce unfairness in ML, Data-driven methods that unintentionally encode existing human biases and introduce new ones.
• Defensive methods to protect Deep Neural Networks (DNNs).
• The success DNNs in image-related applications is threatened by their vulnerability to adversarial settings, including trojan and adversarial sample attacks. A detailed explanation of these types of attacks and countering methods are covered.
• Insider threats are considered one of the most serious and difficult problems to solve, given the privileges and information available to insiders to launch different types of attacks. Current security systems can record and analyze sequences from a deluge of log data, potentially becoming a tool to detect insider threats. The issue is that insiders mix the sequence of attack steps with valid actions, reducing the capacity of security systems to discern long sequences and programmatically detect the executed attacks. M Deep learning-based methods are introduced, which overcome the existing limitations and protect against these types of attacks.
• Monitoring and learning of attacks on autonomous systems and cyber attribution.
• Enhancing Cognitive Autonomy through Deep learning. Autonomous systems, explanation of ML, and actions of autonomous activity with humans in the loop.
• Attacks on space system protocols that use moving target defense and utilizing ML to identify intent and devising methods to mitigate.
• Building recommendation systems. Deep learning in trading: Deep learning to track the market and make trading decisions.
• Privacy-preserving predictive modeling in edge networks, privacy issues in ML used in contact tracing.

Useful Videos from Youtube

• Machine Learning link
• The Agentic Enterprise | WSO2 Technology Conference 2026 link
• Anatomy of AI Agents: Inside LLMs, RAG Systems, & Generative AI: link
• Autism link
• AI Fairness and Bias link
• All Machine Learning Concepts Explained in 22 Minutes link

Class Format

• This is a seminar course. Each class will consist of presentations and discussions. Students will be required to do a class project for the course. A significant portion of the grade will be based on projects and class/research contributions, including paper presentations, contributions to paper reviews, and paper discussions.

Project

• A research class project: Each of you will work on a research project. Group projects are encouraged. The project will be broken down into three assignments: (1) initial research proposal, (2) intermediate report, (3) final report, and presentation.
• Feel free to discuss your ideas with the instructor and propose your own project. The project should have a research component. Project ideas will be outlined in class, but you are responsible for proposing your project. Some background reading is associated with each project. The project proposal (due date SEPT 15) should contain the following information:
  • Topic to be addressed and problem definition.
  • State of the art (prior work, what was done and what needs to be done.)
  • The proposed technique to be advanced, developed and implemented/evaluated.
  • How does your work advance the solution to the problem?.
  • Algorithm proposed, Experiments and Data collected, Conclusions/Guidelines.
  Project proposals should be a couple of pages at most. A project status report is due on Oct 7. The status report should include a description of progress to date and what is expected to be accomplished by the final project presentation day. More details can be found here

Misc

• Class time may be adjusted to accomodate external talks releated to the class.

Reviews are needed for three papers as part of Midterm Exam (Due date: October 19 - Hard copies)

How Papers and Proposals Are Reviewed

Example reviews are shown below.

---

Example of a Journal Paper Review

Comments:

This paper proposes VLMS, a novel post-quantum searchable encryption scheme supporting multi-keyword ranked retrieval and result verification. The work is technically sound, well-motivated, and demonstrates a practical efficiency-accuracy trade-off. The manuscript is strong and requires only minor revisions to improve clarity and consistency before publication.

Strengths:

• Novelty: The work offers a clear contribution to the post-quantum searchable encryption landscape.
• Technical Soundness: The proposed scheme effectively addresses complex challenges (multi-keyword ranking, verification) within a post-quantum framework.
• Evaluation: The experimental evaluation is comprehensive, providing convincing evidence of the scheme's practical potential and favorable performance trade-offs.

Recommended Revisions:

I recommend the authors address the following minor points:

• Rigor of Security Proof: The derivation of Equation 7 in the security proof is too concise. The authors should expand this section to include the intermediate steps, thereby strengthening the proof's rigor.
• Threat Model Consistency: The threat model is described as "honest-but-curious," but the scheme's inclusion of a verification mechanism suggests it also guards against a malicious server that tampers with results. This apparent contradiction should be reconciled, and the threat model section refined accordingly.
• Clarity of Notation: The manuscript's notation is quite dense. Despite the inclusion of a symbol table, it remains challenging to follow. The authors are encouraged to streamline and standardize the notation throughout the paper to enhance readability.
• Typos and Clarity: The paper contains several typographical errors (e.g., "with an an increasing number..." in the abstract; "Resistence to quantum attack" on p. 12) and minor unclear phrasing. The entire manuscript should be carefully proofread to correct these errors.

Additional Questions:

1. Please explain how this manuscript advances this field of research and/or contributes something new to the literature.

   Novelty: The work offers a clear contribution to the post-quantum searchable encryption landscape.

Technical Soundness: The proposed scheme effectively addresses complex challenges (multi-keyword ranking, verification) within a post-quantum framework.

Evaluation: The proposed scheme effectively addresses complex challenges (multi-keyword ranking, verification) within a post-quantum framework.

Is the manuscript technically sound? Please explain your answer under Public Comments below: Appears to be - but didn't check completely

Are the title, abstract, and keywords appropriate? Please explain under Public Comments below: Yes

Does the manuscript contain sufficient and appropriate references? Please explain under Public Comments below: References are sufficient and appropriate

If you are suggesting additional references they must be entered in the text box provided. All suggestions must include full bibliographic information plus a DOI. If you are not suggesting any references, please type NA. NA

Does the introduction state the objectives of the manuscript in terms that encourage the reader to read on? Please explain your answer under Public Comments below: Could be improved

How would you rate the organization of the manuscript? Is it focused? Is the length appropriate for the topic? Please explain under Public Comments below: Could be improved

Please rate the readability of the manuscript. Explain your rating under Public Comments below: Readable - but requires some effort to understand

Should the supplemental material be included? (Click on the Supplementary Files icon to view files): Does not apply, no supplementary files included

If yes to above, should it be accepted: NA

Please rate the manuscript. Explain your choice: Excellent

Please rate the manuscript. Explain your choice: Excellent

---

Criterion of NSF Proposal Reviews

NSF Merit Review Criteria

The two merit review criteria are listed below. Both criteria are to be given full consideration during the review and decision-making processes; each criterion is necessary but neither, by itself, is sufficient. Therefore, proposers must fully address both criteria. (Chapter II.D.2.d(i) contains additional information for use by proposers in development of the Project Description section of the proposal.) Reviewers are strongly encouraged to review the criteria, including Chapter II.D.2.d(i), prior to the review of a proposal.

When evaluating NSF proposals, reviewers will be asked to consider what the proposers want to do, why they want to do it, how they plan to do it, how they will know if they succeed, and what benefits could accrue if the project is successful. These issues apply both to the technical aspects of the proposal and the way in which the project may make broader contributions.

To that end, reviewers will be asked to evaluate all proposals against two criteria:

• Intellectual Merit: The Intellectual Merit criterion encompasses the potential to advance knowledge.
• Broader Impacts: The Broader Impacts criterion encompasses the potential to benefit society and contribute to the achievement of specific, desired societal outcomes.

The following elements should be considered in the review for both criteria:

• What is the potential for the proposed activity to:
  1. Advance knowledge and understanding within its own field or across different fields (Intellectual Merit); and
  2. Benefit society or advance desired societal outcomes (Broader Impacts)?
• To what extent do the proposed activities suggest and explore creative, original, or potentially transformative concepts?
• Is the plan for carrying out the proposed activities well-reasoned, well-organized, and based on a sound rationale? Does the plan incorporate a mechanism to assess success?
• How well qualified is the individual, team, or organization to conduct the proposed activities?
• Are there adequate resources available to the PI (either at the home organization or through collaborations) to carry out the proposed activities?

---

Summary of weights per category

Item	Weight
Written research paper/report	20%
Class presentations, participation, and discussion	15%
Mid Term Examination	25%
Projects	40%

Situational Knowledge

Machine Learning

Adversarial Machine Learning

• Responsible and Trusted AI, Alina and Palash
• Fairness and Bias in ML, Palash
• The pursuit of responsible AI raises the ante on both the trustworthy computing and formal methods communities.

Talks

• Towards Interpretable, Trustworthy Machine Learning for Science , Lin, Purdue University, 2025.
• Seeing Beyond Data: Futures of Semantic Intelligence , Carmel, American University, 2025.
• Towards Interpretable, Trustworthy Machine Learning for Science , Lin, Purdue University, 2025.
• Toward an End-to-end Anomaly Discovery System , Cao, MIT, 2020.
• Automating Collusion Detection in Sequential Games , Mazrooei, Archibald, and Bowling, Purdue University, 2013.
• Reinforcement Learning , Aggarwal, Purdue University, 2020.
• Abstract for COVID conference , Bhargava, Purdue University, 2020.
• Covid and AI/ML/DS , Bhargava, Purdue University, 2020.
• A Deep Learning Approach for Tweet Classification for Effective Disaster Management , Madria, 2020.
• Explainable AI , Vishnu S. Penubarthi and Lalana Kagel, MIT, 2020.
• CoronaVis: A Real-time COVID-19 Tweets Analyzer , Kabir and Madria, 2020.
• Towards Effective Interpretation of Deep Neural Networks: Algorithms and Applications , Hu, Texas A&M University, 2020.
• Learning with Weak Social Supervision for Disinformation Detection , Shu, IIT-Chicago, 2020.

Spring 2026 Student Project Presentations

• Group 1 - Explainable Financial Forecasting [Presentation Slides], Kevin Cushing, Anik Dey, and Aarav Sane.
• Group 2 - WatchStress [Presentation Slides],Winston Lin.
• Group 3 - Code translation with transformers [Presentation Slides],Tejas Yalamanchili and Shrinivas Venkatesan.
• Group 4 - LLMs and the prisoner's dilemma [Presentation Slides],(Related Paper), Vanshika Balaji, and Anish Kambhampati.
• Group 5 - Interpretable detection of dental abnormalities, Ayush Karamcharya
• Group 6 - Bridging the trust gap in the medical field,(paper presentation) Bhargavi Katuru
• Group 7 - A Multi-agent collaborative framework for automated tabular data cleaning,(Related Paper), Yibo Wang, and Riteng Zhang
• Group 8 - Viewpoint and occlusion effects in single-view 3D reconstruction,(Related Paper), Enze Wang
• Group 9 - Explainable AI in Foundation Models, Rajiv Ranjan
• Group 10 - Collaborative attacks extend, Zizheng Liu
• Group 11 - Pneumonia Detection & Explainable AI, Dheeraj Namargomala
• Group 12 - How do I know that dude?, Tri Vo
• Group 13 - Explainable Fake News Detection ,(Related Paper), Soham Sharma
• Group 14 - Explainable Mobility Predictions and POI Recommendations, Shiveswarran R
• Group 15 - Automated Rule Generation for Fraud Detection,(Related Paper 1),(Related Paper 2), Manmeet Dang and Sashank silwal
• Group x - Vector Search Introduction [Presentation Slides],Yinghao He

Fall 2026 Student Project Presentations

• Group 1 - [Presentation Slides],(Related Paper), Ryan Peters.
• Group 2 - LLM sycophancy [Presentation Slides], Yinghao He.
• Group 3 - Loss Landscape Analysis [Presentation Slides], Mashiat Mustaq.

Science of Artificial Intelligence and Learning for Open-world Novelty (SAIL-ON)

• SAIL-ON: Science of Artificial Intelligence and Learning for Open-world Novelty

Other resources

• AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
• Find Them Video by Purdue/MIT authors [Video]
• Recognizing person who needs help by MIT/Purdue authors [Video]
• All Machine Learning algorithms explained in 17 min by Infinite Codes [Video]
• Alan Turing Institute: Future of Generative AI [Video]
• IBM Technology : 7 AI terms you need to know: AI, RAG and more [Video]
• IBM Technology: Generative vs Agentic AI: Shaping the Future of AI Collaboration [Video]
• IBM Technology: What is RAG [Video]
• Kodecloud:RAG Explained For Beginners [Video]
• Large Language Models explained briefly by 3Blue1Brown [Video]
• How large Language Models work by IBM Technology [Video]
• Assisting West Lafayette police in identifying persons who are differently abled [Presentation Slides], Bhargava, Purdue University, 2019.
• Autism Information for Law Enforcement and Other First Responders Autism Society
• Autism video of police dashcam Youtube Video Youtube Video 2 Instagram post Facebook post Today News Youtube_NBC Video WFSB News
• Enhancing the Interpretability of SHAP Values Using Large Language Models, Zheng, X., 2024
• Attack in networks

• Could Collecting Missing Values During Inference Change the Prediction
[Paper]

• SNAP
• OpenAG Data Alliance (OADA)
• Videos from NYC
• The Stanford Open Policing Project
• West Lafayette police data

• MIT 6.S191: AI Bias and Fairness by Alexander Amini, (Course Link)
• Ontology-Regularized Multimodal Neural Networks for Explainable Mental Health Assessment, Bhavya J. et al , ISIC 2025
• REFRESH: Responsible and Efficient Feature Reselection guided by SHAP values by Shubham Sharma (JPM Presentation slide) (JPM recording)
• Context-aware SHAP for responsible feature selection, Sivapriya V. et al, 2024
• Counterfactual Shapley Additive Explanations, Emanuele A. et al, 2022
• Which LIME should I trust? Concepts, Challenge, and Solutions, Knab, P. et al, 2025
• Explainable AI - An Overview (Presentation 1) by Trevor Bonjour
• Explainable AI - An Overview (Presentation 2) by Trevor Bonjour
• Darpa XAI: A retrospective
• Explainable AI Darpa
• Explainable AI Darpa for NASA
• Explainable AI in Critical Domains: From Theory to Trusted Applications
• DARPA-BAA-16-53
• Paper on Explainable AI
• Triage proposal
• A Snapshot of the Frontiers of Fairness in Machine Learning [Video], Chouldechova and Roth, CACM, 2020
• Techniques for Interpretable Machine Learning, Du, Liu, and Hu, 2020
• Techniques for Interpretable Machine Learning [Video], Du, Liu, and Hu, 2020
• Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning [Paper], Gilpin et al., arXiv, 2018
• Trustworthy Autonomous Systems [Presentation Slides], Kagal et al., MIT, 2018
• Trustworthy Autonomous Systems [Abstract], Kagal et al., MIT, 2018
• Explainable AI(XAI) - AN OVERVIEW by Trevor Bonjour
• Multimodal Explainable AI by Trevor Bonjour
• Bias in ML by Mijanur Palash
• A Snapshot of the Frontiers of Fairness in Machine Learning
• A Snapshot of the Frontiers of Fairness in Machine Learning [Video]
• Techniques for Interpretable Machine Learning
• Techniques for Interpretable Machine Learning [Video]

• Following chapters are for use only by CS 590EAI

  Book: Explainable AI in Critical Domains: From Theory to Trusted Applications, edited by Sarika Jain, Sven Groppe, Prabhjot Kaur, and Bharat Bhargava.

  Copyright: Nova Science Publishers, Inc. (PRINT)

  • A Survey on Bias and Fairness in Machine Learning
  • Explainable AI: Chapter 1
  • Explainable AI: Chapter 2
  • Explainable AI: Chapter 3
  • Explainable AI: Chapter 4
  • Explainable AI: Chapter 5
  • Explainable AI: Chapter 6
  • Explainable AI: Chapter 7
  • Explainable AI: Chapter 8
  • Explainable AI: Chapter 9
  • Explainable AI: Chapter 10
  • Explainable AI: Chapter 11
  • Explainable AI: Chapter 12
  • Explainable AI: Chapter 13
  • Explainable AI: Chapter 15

Outside speakers from MIT, CMU, Northrop Grumman, Sandia, IBM, Missouri Institute of Science and Technology, EPFL, University of Bern and Purdue (ECE, IE, CS) have been invited.

Dawn project at Stanford https://dawn.cs.stanford.edu/

Professor Bhagava: Office: LWSN 2116F, Wednesday 11-11:20 (before class) and 12:20-12:50pm (after class) (more times will be added after discussing with class) and by appointment. email: bbshail at cs purdue edu Phone: (765).413.7312 call anytime.

Project deliverables have a firm deadline. Extensions may only be granted in the case of a severe medical or family emergency.

If you become quarantined or isolated at any point in time during the semester, in addition to support from the Protect Purdue Health Center, you will also have access to an Academic Case Manager who can provide you academic support during this time. Your Academic Case Manager can be reached at acmq@purdue.edu and will provide you with general guidelines/resources around communicating with your instructors, be available for academic support, and offer suggestions for how to be successful when learning remotely. Importantly, if you find yourself too sick to progress in the course, notify your academic case manager and notify me via email. We will make arrangements based on your particular situation. The Office of the Dean of Students (odos@purdue.edu) is also available to support you should this situation occur.

The Protect Purdue Plan, which includes the Protect Purdue Pledge, is campus policy and as such all members of the Purdue community must comply with the required health and safety guidelines. Required behaviors in this class include: staying home and contacting the Protect Purdue Health Center (496-INFO) if you feel ill or know you have been exposed to the virus, wearing a mask in classrooms and campus building, at all times (e.g., no eating/drinking in the classroom), disinfecting desk/workspace prior to and after use, maintaining proper social distancing with peers and instructors (including when entering/exiting classrooms), refraining from moving furniture, avoiding shared use of personal items, maintaining robust hygiene (e.g., handwashing, disposal of tissues) prior to, during and after class, and following all safety directions from the instructor. Students who are not engaging in these behaviors (e.g., wearing a mask) will be offered the opportunity to comply. If non-compliance continues, possible results include instructors asking the student to leave class and instructors dismissing the whole class. Students who do not comply with the required health behaviors are violating the University Code of Conduct and will be reported to the Dean of Students Office with sanctions ranging from educational requirements to dismissal from the university. Any student who has substantial reason to believe that another person in a campus room (e.g., classroom) is threatening the safety of others by not complying (e.g., not wearing a mask) may leave the room without consequence. The student is encouraged to report the behavior to and discuss next steps with their instructor. Students also have the option of reporting the behavior to the Office of the Student Rights and Responsibilities. See also Purdue University Bill of Student Rights.

Academic integrity is one of the highest values that Purdue University holds. Individuals are encouraged to alert university officials to potential breaches of this value by either emailing integrity@purdue.edu or by calling 765-494-8778. While information may be submitted anonymously, the more information is submitted the greater the opportunity for the university to investigate the concern. More details are available on our course Brightspace table of contents, under University Policies.

Purdue University is committed to maintaining a community which recognizes and values the inherent worth and dignity of every person; fosters tolerance, sensitivity, understanding, and mutual respect among its members; and encourages each individual to strive to reach his or her own potential. In pursuit of its goal of academic excellence, the University seeks to develop and nurture diversity. The University believes that diversity among its many members strengthens the institution, stimulates creativity, promotes the exchange of ideas, and enriches campus life. More details are available on our course Brightspace table of contents, under University Policies.

The Disability Resource Center (DRC) is a resource for students and instructors. Students may present a “Letter of Accommodation” to you at any point in the semester. Should you have questions about accommodations, please contact the DRC at 765-494-1247 or email. In many cases, the DRC can partner with you to develop inclusive teaching strategies that benefit all students in your class. Purdue University strives to make learning experiences as accessible as possible. If you anticipate or experience physical or academic barriers based on disability, you are welcome to let me know so that we can discuss options. You are also encouraged to contact the Disability Resource Center at: drc@purdue.edu or by phone: 765-494-1247. More details are available on our course Brightspace under Accessibility Information.

If you find yourself beginning to feel some stress, anxiety and/or feeling slightly overwhelmed, try WellTrack. Sign in and find information and tools at your fingertips, available to you at any time. If you need support and information about options and resources, please contact or see the Office of the Dean of Students. Call 765-494-1747. Hours of operation are M-F, 8 am- 5 pm. If you find yourself struggling to find a healthy balance between academics, social life, stress, etc. sign up for free one-on-one virtual or in-person sessions. with a Purdue Wellness Coach at RecWell. Student coaches can help you navigate through barriers and challenges toward your goals throughout the semester. Sign up is completely free and can be done on BoilerConnect. If you have any questions, please contact Purdue Wellness at evans240@purdue.edu. If you’re struggling and need mental health services: Purdue University is committed to advancing the mental health and well-being of its students. If you or someone you know is feeling overwhelmed, depressed, and/or in need of mental health support, services are available. For help, such individuals should contact Counseling and Psychological Services (CAPS) at 765-494-6995 during and after hours, on weekends and holidays, or by going to the CAPS office of the second floor of the Purdue University Student Health Center (PUSH) during business hours.

In the event of a major campus emergency, course requirements, deadlines and grading percentages are subject to changes that may be necessitated by a revised semester calendar or other circumstances beyond the instructor's control. Relevant changes to this course will be posted onto the course website or can be obtained by contacting the instructors or TAs via email or phone. You are expected to read your @purdue.edu email on a frequent basis.

Old web page with more content(Mar 30, 2026)

The template of this website was created by: HazyReseach@Stanford Modified by: servio@palacios.com.