Amrita Bhattacharjee
PhD Candidate, specializing in LLM Safety
Phoenix, Arizona, United States
Actions
Amrita is a PhD candidate at the Data Mining and Machine Learning lab at Arizona State University. Her research primarily focuses on: (i) responsibly leveraging large language models (LLMs) for human-intensive tasks in machine learning pipelines, (ii) safety and robustness of LLMs, (iii) robust detection of AI-generated content. Her work has resulted in over 20 peer-reviewed publications, with ~500 citations, and 3 provisional patent filings. Her work has received recognition via the Outstanding Paper Award at AACL 2023. During her time at NVIDIA NeMo Guardrails, she contributed by proposing a new research direction of inference-time safety steering for LLMs, resulting in a novel framework. Alongside her research, she is actively involved in the community via serving on the Program Committee for multiple conferences such as IJCAI, AAAI, SDM, etc., mentoring students and early career researchers, and speaking about recent developments in AI, GenAI and LLM research.
Links
Topics
Building Trust in AI: On Safe and Responsible Use of LLMs
Generative AI and in particular large language models (LLMs) have revolutionized many facets of everyday life and are here to stay. While AI and LLMs have demonstrated incredible potential as productivity aids, malicious uses and undesirable effects of such technologies are also on the rise. Given this current landscape, in this talk I will focus on the following broad topics:
1. Overview of the state of generative AI and LLM development.
2. Overview of current use cases and success stories of LLM development and deployment in specific domains
3. Focus on threats and mitigation strategies:
- LLM-generated disinformation
- LLMs when used for social engineering attacks
- Ease of attacking LLMs, types of attacks
- Why LLM safety training fails
- Efficient alternatives to safety training, with a focus on inference-time safety steering.
4. Best practices and takeaways.
CactusCon 13 Sessionize Event
Amrita Bhattacharjee
PhD Candidate, specializing in LLM Safety
Phoenix, Arizona, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top