7 citations · 9 across the 7 of their papers we have counts for
8 papers
Jailbroken Frontier Models Retain Their Capabilities
Daniel Zhu, Zihan Wang, Xuchan Bao +1
As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this complexity imposes a "jailbr…
Segment-Level Coherence for Robust Harmful Intent Probing in LLMs
Xuanli He, Bilgehan Sel, Faizan Ali +3
Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although…
Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size
Dikshant Kukreja, Kshitij Sah, Gautam Gupta +5
Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formali…
Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
Bilgehan Sel, Xuanli He, Alwin Peng +2
Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an a…
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Hoagy Cunningham, Jerry Wei, Zihan Wang +26
We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to prev…
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu +40
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…
Non-robustness of diffusion estimates on networks with measurement error
Arun G. Chandrasekhar, Paul Goldsmith-Pinkham, Tyler H. McCormick +2
Network diffusion models are used to study disease transmission, information spread, technology adoption, and other socio-economic processes. We show that estimates of these diffus…
Robust Semantic Interpretability: Revisiting Concept Activation Vectors
Jacob Pfau, Albert T. Young, Jerome Wei +2
Interpretability methods for image classification assess model trustworthiness by attempting to expose whether the model is systematically biased or attending to the same cues as a…