activity
20242026
collaborators

7 papers

cs.LG2026

CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment

Anurag Kumar, Raghuveer Peri, Jon Burnsky +4

Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a highe…

cs.LG2025

A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning

Zhe Wang, Yanjun Qi

Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a c…

cs.CR2025

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation

Daniel Schwartz, Dmitriy Bespalov, Zhe Wang +2

As large language models (LLMs) become increasingly prevalent, ensuring their robustness against adversarial misuse is crucial. This paper introduces the GAP (Graph of Attacks with…

cs.CL2025

LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning

Zifan Xu, Haozhu Wang, Dmitriy Bespalov +3

Chain-of-thought (CoT) prompting is a popular in-context learning (ICL) approach for large language models (LLMs), especially when tackling complex reasoning tasks. Traditional ICL…

cs.CR2025

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice

Aman Goel, Xian Carrie Wu, Zhe Wang +2

Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit u…

cs.CR2025

TaeBench: Improving Quality of Toxic Adversarial Examples

Xuan Zhu, Dmitriy Bespalov, Liwen You +2

Toxicity text detectors can be vulnerable to adversarial examples - small perturbations to input text that fool the systems into wrong detection. Existing attack algorithms are tim…