28 June, 2024: Pune Institute of Computer Technology (PICT), Pune
50+ Participants, including students from closeby other ACM Student chapters.
Title of the talk: Responsible & Safe AI consisting of {graph, machine} unlearning, RLHF, alignment problem, jail breaking, interpretability, bias, and more.

    

27 March, 2024: Bharati Vidyapeeth University, Department of Engineering & Technology, Navi Mumbai
100+ Participants, including students from closeby other ACM Student chapters.
Title of the talk: Responsible & Safe AI

    

13 Dec, 2023: KL University Hyderabad Bachupally Campus
250+ Participants, including ACM Student chapter inauguration.
Title of the talk: Responsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBias

    

April 26, 2019: PSG College of Technology.
60+ participants attended.

    

April 2, 2019: Rishi M.S Institute of Engineering & Technology for Women, Hyderabad.
100+ participants attended.

    

Jan 9, 2019: BVRIT Hyderabad.
120+ participants attended.

    

October 24, 2018: VNR Vignana Jyothi Institute of Engineering and Technology (VJIET), Hyderabad.
150+ participants attended.

    

         

September 20, 2018: Sasi Institute of Technology and Engineering, Andhra Pradesh.
200+ participants attended.

    

July 28, 2018: Kalasalingam Academy of Research and Education, Krishnan Kovil.
140+ participants attended.

    

         

July 27, 2018: Thiagarajar College of Engineering, Madurai.
180+ participants attended.

    

Mar 17, 2018: Maharaja Agrasen Institute of Technology, Delhi
100+ participants attended the talk

    

Feb 20, 2018: BITS Pilani, Pilani
30+ participants attended the talk

    

Feb 16, 2018: BITS Pilani, Hyderabad
40+ participants attended the talk

    

Feb 15, 2018: Indian Institute of Technology, Hyderabad
20+ participants attended the talk

    

Jan 25, 2018: Department of Computer Science, Bennett University
60+ participants attended the talk

    

Nov 15, 2017: Shiv Nadar University, Noida
60+ participants attended the talk

Mar 8, 2017: S.A. Engineering College, Chennai
70+ participants attended the talk

Feb 22, 2017: Manav Rachna International University, Faridabad
100+ participants attended the talk

Nov 21, 2016: Indian Institute of Technology, Kharagpur
40+ participants attended the talk

Sept 27, 2016: Indian Institute of Technology, Guwahati
75+ participants attended the talk

June 6, 2016: Indira Gandhi Technical University for Women, New Delhi
50+ participants attended the workshop

    

Feb 17, 2016: Bharati Vidyapeeth College of Engineering, New Delhi
100+ participants attended the talk

Sept 14, 2015: ITM University, Gurgaon
180+ participants attended the talk

    

July 22, 2015: Infosys Bengaluru
80+ participants attended the talk

    

July 22, 2015: IIIT Bengaluru
15+ participants attended the talk

    

March 16, 2015: Jaypee Institute of Information Technology, NOIDA
140+ participants attended the talk

    

Dec 18, 2014: Coimbatore Institute of Technology (CIT), Coimbatore
120+ participants attended the talk

        

Dec 17, 2014: PSG College of Technology, Coimbatore
40+ participants attended the talk

September 13, 2014: ACM Regional Event on CyberSecurity, Pune.
Attended by 70+ participants. Picture with a few of the participants.

March 26, 2014: Thapar Univiersity

    

Talk Zero: Ethical, Responsible, and Safe Requirements for AI
Abstract: In a world increasingly shaped by AI technologies, including influential models like GPT-4, LLaMA, Stable Diffusion, and DALL.E, common applications of AI in natural language understanding, image generation, and more are prominent. There is an increased use of AI models in various applications, from enhancing customer service interactions to enabling creative image generation and autonomous vehicles. One can now use specialized GPTs for a variety of use cases through a AppStore-like AI marketplace, straight out-of-the-box. However, with great power comes great responsibility, and it's imperative to acknowledge the technical, ethical, responsible, and fairness issues that accompany these powerful systems. Zooming out to the bigger picture, the talk will address the criticality of identifying ethical, responsible, and safe requirements for AI systems. Will cover some super exciting ongoing research projects at Precog Lab -- methods to improve interpretability [ICML 2024], consistency [LREC-COLING 2024], Continual learning [NeurIPS 2024], detecting AI generated Hindi text [EMNLP 2024] and the removal of harmful labels and knowledge from these models [ICML 2024]. ChatGPT was used to edit / polish this Abstract :)
[ICML 2024] Representation Surgery: Theory and Practice of Affine Steering. [Link]
[ICML 2024] The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning. [Link]
[NeurIPS 2024] Random Representations Outperform Online Continually Learned Representations [Link]
[EMNLP 2024] Counter Turing Test (CT2): Investigating AI-Generated Text Detection for Hindi. [Link]
[LREC-COLING 2024] SaGE: Evaluating Moral Consistency in Large Language Models. [Link]
[Under review] COBIAS: Contextual Reliability in Bias Assessment. [Link]

Talk one: Data Science for Social Good
Abstract: With increase in sage of the Internet, social media platforms, huge amount of data is getting generated at various level; one of the dire need of the hour is to see how we can use this data to have societal impact. I will briefly mention some super cool projects that we have worked on and that have made some visible contributions to the world outside academia. All work presented in the talk (including datasets, code, slides, recorded videos) has related publications at https://precog.iiit.ac.in/ Projects that I will touch upon are — Selfie deaths / KillFie http://labs.precog.iiitd.edu.in/killfie/ #GeneralElections2019 http://bit.ly/elections19(Mis)Information / Fake content on Twitter, Facebook, and WhatsApp, and Computing for Medicine. We all understand, many real world problems cannot be addressed by a single domain faculty / researcher, we need more students & faculty to come together, hoping to generate some interest to join hands to have an impact and make a difference. Many of our research work is made available for public use through tools or online services at https://precog.iiit.ac.in/ including datasets that we have used in our research work. Our work derives techniques from Computational Social Science, Data Science, Statistics, and Network Science. I will be more than happy to clarify, discuss, any of our work in detail, as required, after the talk.

Talk two: "Privacy and Security in Online Social Media (PSOSM)"
Abstract: With increase in usage of the Internet, there has been an exponential increase in the use of online social media on the Internet. Websites like Facebook, Instagram, Twitter, Tinder, YouTube, and many others have changed the way the Internet is being used. There is a dire need to investigate, measure, and understand privacy and security on online social media from various perspectives (computational, cultural, psychological). Real world scalable systems need to be built to detect and defend security and privacy issues on online social media. I will describe briefly some cool projects that we work on: (Mis)Information / Fake content on Twitter, Facebook, and WhatsApp; Linking profiles across different social networks; Selfie deaths and KillFies; and Manipulated followers. Many of our research work is made available for public use through tools or online services at precog.iiit.ac.in including datasets that we have used in our research work. Our work derives techniques from Computational Social Science, Data Science, Statistics, and Network Science. I will be more than happy to clarify, discuss, any of our work in detail, as required, after the talk.

Talk three: Social Computing for Medicine
Abstract: With increase in importance of computing in healthcare, there has been an exponential increase in use of computing methodologies to develop better understanding of health care systems. In the history of human lives, Health and Medicine have never seen the importance as it has in the current scenario. Perhaps for the first time in the history of democratic India, healthcare is predicted to play an important role in future election manifestos as well. I will briefly describe some cool projects that we are currently working on - WASHKaro http://precog.iiitd.edu.in/research/c4m to provide right information at the right time during pandemic situations like #COVID19; use social media as a source to study mental health & early understanding of psychological patterns of users http://covibes.tavlab.iiitd.edu.in/; build transparent Agent Based Models, classical compartmental models to allow interactions with the assumptions like lockdown, testing, & social interventions. covision http://covision.tavlab.iiitd.edu.in/ a system that we build to showcase these models. The talk will end with showcasing some grand challenges that I see in this space which can be a great starting point for students interested in pursuing research and solving some real world problems. Many of our research work is made available for public use through tools or online services at precog.iiit.ac.in including datasets that we use for research. Our work derives techniques from Social Computing, Computational Social Science, Machine Learning, Statistics, and Network Science. I will be more than happy to clarify, discuss, any of our work in detail, as required, after the talk.

PK can be reached at pk.guru@iiit.ac.in.