7 citations · 22 across the 14 of their papers we have counts for
16 papers
Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents
Xu Li, Simon Yu, Minzhou Pan +4
Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way. Yet they show limited backup a…
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails
Mingyang Song, Luxin Xu, Haoyu Sun +3
Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image. Real deployments are different: t…
AIR-BENCH Live: An Evolving Safety Benchmark for Foundation Models
Rohan Naphade, Minzhou Pan, Bo Li
Foundation-model safety benchmarks capture the AI risks of their time of publication: as models improve and governments pass new AI-safety legislation, their risk taxonomies become…
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
Xu Li, Simon Yu, Minzhou Pan +5
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in m…
SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability
Peiyang Xu, Minzhou Pan, Zhaorun Chen +3
With the rapid proliferation of digital media, the need for efficient and transparent safeguards against unsafe content is more critical than ever. Traditional image guardrail mode…
ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
Zhaorun Chen, Xun Liu, Mintong Kang +4
As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Exis…
Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
Mintong Kang, Zhaorun Chen, Chejian Xu +6
As LLMs become widespread across diverse applications, concerns about the security and safety of LLM interactions have intensified. Numerous guardrail models and benchmarks have be…
SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
Zhaorun Chen, Francesco Pinto, Minzhou Pan +1
With the rise of generative AI and rapid growth of high-quality video generation, video guardrails have become more crucial than ever to ensure safety and security across platforms…
AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies
Yi Zeng, Yu Yang, Andy Zhou +9
Foundation models (FMs) provide societal benefits but also amplify risks. Governments, companies, and researchers have proposed regulatory frameworks, acceptable use policies, and…
AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies
Yi Zeng, Kevin Klyman, Andy Zhou +6
We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a sig…
Evaluating and Mitigating IP Infringement in Visual Generative AI
Zhenting Wang, Chen Chen, Vikash Sehwag +2
The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered…
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
Minzhou Pan, Yi Zeng, Xue Lin +4
In this study, we investigate the vulnerability of image watermarks to diffusion-model-based image editing, a challenge exacerbated by the computational cost of accessing gradient…
Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
Minzhou Pan, Zhenting Wang, Xin Dong +3
In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting. WMD is capable of detecting arbit…
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms
Minzhou Pan, Yi Zeng, Lingjuan Lyu +2
Backdoor data detection is traditionally studied in an end-to-end supervised learning (SL) setting. However, recent years have seen the proliferating adoption of self-supervised le…
How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?
Yi Zeng, Minzhou Pan, Himanshu Jahagirdar +3
Given the volume of data needed to train modern machine learning models, external suppliers are increasingly used. However, incorporating external data poses data poisoning risks,…
Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
Yi Zeng, Minzhou Pan, Hoang Anh Just +3
Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware spe…