11 citations · 38 across the 17 of their papers we have counts for
12 papers · 1 filter
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
Yangsibo Huang, Daogao Liu, Lynn Chua +7
Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expos…
On Memorization of Large Language Models in Logical Reasoning
Chulin Xie, Yangsibo Huang, Chiyuan Zhang +6
Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when…
An Adversarial Perspective on Machine Unlearning for AI Safety
Jakub Łucki, Boyi Wei, Yangsibo Huang +3
Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazard…
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
Weijia Shi, Jaechan Lee, Yangsibo Huang +7
Language models (LMs) are trained on vast amounts of text data, which may include private and copyrighted content. Data owners may request the removal of their data from a trained…
Evaluating Copyright Takedown Methods for Language Models
Boyi Wei, Weijia Shi, Yangsibo Huang +5
Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content…
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
Lynn Chua, Badih Ghazi, Yangsibo Huang +6
Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, i.e…
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
Tinghao Xie, Xiangyu Qi, Yi Zeng +13
Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts…
Fantastic Copyrighted Beasts and How (Not) to Generate Them
Luxi He, Yangsibo Huang, Weijia Shi +7
Recent studies show that image and video generation models can be prompted to reproduce copyrighted content from their training data, raising serious legal concerns about copyright…
Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
Lynn Chua, Badih Ghazi, Yangsibo Huang +6
Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive dat…
AI Risk Management Should Incorporate Both Safety and Security
Xiangyu Qi, Yangsibo Huang, Yi Zeng +22
The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety…
A Safe Harbor for AI Evaluation and Red Teaming
Shayne Longpre, Sayash Kapoor, Kevin Klyman +20
Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by promi…
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Boyi Wei, Kaixuan Huang, Yangsibo Huang +6
Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This stu…