5 citations · 5 across the 18 of their papers we have counts for
20 papers
Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses
Weichen Yu, Lesly Miculicich, Bhavana Dalvi Mishra +5
Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback. Existing approaches, however…
Steal the Patch Size: Adversarially Manipulate Vision-Language Models
Kai Hu, Akash Bharadwaj, Weichen Yu +1
We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and in…
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
Weichen Yu, Xiaomin Li, Yizhou Zhao +8
Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning s…
A New Framework for Cybersecurity Refusals in AI Agents
Eliot Krzysztof Jones, Mateusz Dziemian, Matt Fredrikson +1
Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existin…
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…
SecCodePRM: A Process Reward Model for Code Security
Weichen Yu, Ravi Mangal, Yinyi Luo +4
Large Language Models are rapidly becoming core components of modern software development workflows, yet ensuring code security remains challenging. Existing vulnerability detectio…
Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
Xiaoze Liu, Ruowang Zhang, Weichen Yu +7
Heterogeneous multi-agent systems combine models with different capabilities through a common communication interface. Exchanging internal states directly requires translating betw…
LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models
Kai Hu, Haoqi Hu, Matt Fredrikson
Lipschitz-based certification offers efficient, deterministic robustness guarantees but has struggled to scale in model size, training efficiency, and ImageNet performance. We intr…
PrivCode: When Code Generation Meets Differential Privacy
Zheng Liu, Chen Gong, Terry Yue Zhuo +4
Large language models (LLMs) have presented outstanding performance in code generation and completion. However, fine-tuning these models on private datasets can raise privacy and p…
When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
Xiaoze Liu, Weichen Yu, Matt Fredrikson +2
Tokenizer transplant in cross-vocabulary model composition reconstructs donor-only embedding rows as weighted combinations over shared lexical anchors and reuses those coefficients…
Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
Kai Hu, Abhinav Aggarwal, Mehran Khodabandeh +6
This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model (LLM) safety evaluation from a constrained example-based appr…
Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
Justin W. Lin, Eliot Krzysztof Jones, Donovan Julian Jasper +10
We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals a…
D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
Satyapriya Krishna, Andy Zou, Rahul Gupta +6
The safety and alignment of Large Language Models (LLMs) are critical for their responsible deployment. Current evaluation methods predominantly focus on identifying and preventing…
Evaluating Language Model Reasoning about Confidential Information
Dylan Sam, Alexander Robey, Andy Zou +2
As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concer…
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
Andy Zou, Maxwell Lin, Eliot Jones +14
Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these sys…
A Mixture of Linear Corrections Generates Secure Code
Weichen Yu, Ravi Mangal, Terry Zhuo +2
Large language models (LLMs) have become proficient at sophisticated code-generation tasks, yet remain ineffective at reliably detecting or avoiding code vulnerabilities. Does this…
Adversarial Attacks on Robotic Vision Language Action Models
Eliot Krzysztof Jones, Alexander Robey, Andy Zou +5
The emergence of vision-language-action models (VLAs) for end-to-end control is reshaping the field of robotics by enabling the fusion of multimodal sensory inputs at the billion-p…
Transferable Adversarial Attacks on Black-Box Vision-Language Models
Kai Hu, Weichen Yu, Li Zhang +5
Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversa…
Is Your Text-to-Image Model Robust to Caption Noise?
Weichen Yu, Ziyan Yang, Shanchuan Lin +5
In text-to-image (T2I) generation, a prevalent training technique involves utilizing Vision Language Models (VLMs) for image re-captioning. Even though VLMs are known to exhibit ha…
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian +11
The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as s…