15 citations · 35 across the 12 of their papers we have counts for
12 papers
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
Yizhe Zeng, Wei Zhang, Yunpeng Li +3
While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack s…
SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…
AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
Andy Zhou, Kevin Wu, Francesco Pinto +7
As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vul…
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Chejian Xu, Jiawei Zhang, Zhaorun Chen +22
Multimodal foundation models (MMFMs) play a crucial role in various applications, including autonomous driving, healthcare, and virtual assistants. However, several studies have re…
International AI Safety Report
Yoshua Bengio, Sören Mindermann, Daniel Privitera +93
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by…
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Chengquan Guo, Xun Liu, Chulin Xie +5
With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant ba…
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…
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
Yi Zeng, Weiyu Sun, Tran Ngoc Huynh +3
Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionali…
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…
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…
Introducing v0.5 of the AI Safety Benchmark from MLCommons
Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed +97
This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safe…