3 citations · 4 across the 9 of their papers we have counts for
11 papers
Guided Diffusion for Trustworthy Synthetic Text Generation
Qi Pang, Hanshen Xiao, Andre Manoel +4
The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks, as models can inadvertently memorize and even directly out…
Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion
Qi Pang, Virginia Smith, Wenting Zheng
Multi-agent systems built on large language models (LLMs) are increasingly deployed in high-stakes settings such as finance, healthcare, and software engineering, where agents coor…
Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness
Varshini Elangovan, James Wedgwood, Chhavi Yadav +3
Conversational AI systems can pose safety risks to their users such as hallucination, sycophancy, overconfidence, and anthropomorphism, but these risks are difficult for users to d…
Personalization, Personas, and Forecasting in Value Alignment
James Wedgwood, Pratiksha Thaker, Neil Kale +1
LLM behavior may be conditioned by human identity in several ways: they may be asked to adapt to users, role-play populations, or forecast how people would answer value-laden quest…
Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety
Neil Kale, Rebecca Portnoff, Pratiksha Thaker +5
Modern artificial intelligence (AI) systems present profound new risks to child safety. AI is increasingly being misused to create AI-generated child sexual abuse material, facilit…
Membership Inference Attacks for Unseen Classes
Pratiksha Thaker, Neil Kale, Zhiwei Steven Wu +1
A key tool in developing safe AI models is \emph{data auditing}, i.e., using statistical tools to determine whether harmful content may have been used in the training data of a bla…
BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
Shengyuan Hu, Neil Kale, Pratiksha Thaker +3
Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning invo…
Position: LLM Unlearning Benchmarks are Weak Measures of Progress
Pratiksha Thaker, Shengyuan Hu, Neil Kale +3
Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning re…
Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu +1
Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning…
Privacy Amplification for the Gaussian Mechanism via Bounded Support
Shengyuan Hu, Saeed Mahloujifar, Virginia Smith +2
Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individual…
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
Qi Pang, Shengyuan Hu, Wenting Zheng +1
Advances in generative models have made it possible for AI-generated text, code, and images to mirror human-generated content in many applications. Watermarking, a technique that a…