A Survey on Safety-Critical Driving Scenario Generation-A Methodological Perspective von Ding, Wenhao, Xu, Chejian, Arief, Mansur, Lin, Haohong, Li, Bo, Zhao, Ding

Volltext

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models von Kang, Mintong, Xu, Chejian, Li, Bo

Volltext bestellen

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles von Zhang, Jiawei, Xu, Chejian, Li, Bo

Volltext bestellen

COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks von Huang, Zijian, Chu, Wenda, Li, Linyi, Xu, Chejian, Li, Bo

Volltext bestellen

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities von Xu, Peng, Ping, Wei, Wu, Xianchao, Xu, Chejian, Liu, Zihan, Shoeybi, Mohammad, Catanzaro, Bryan

Volltext bestellen

AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents von Xu, Chejian, Kang, Mintong, Zhang, Jiawei, Liao, Zeyi, Mo, Lingbo, Yuan, Mengqi, Sun, Huan, Li, Bo

Volltext bestellen

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models von Kang, Mintong, Xu, Chejian, Li, Bo

Volltext

KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking von Zhang, Jiawei, Xu, Chejian, Gai, Yu, Lecue, Freddy, Song, Dawn, Li, Bo

Volltext bestellen

SemAttack: Natural Textual Attacks via Different Semantic Spaces von Wang, Boxin, Xu, Chejian, Liu, Xiangyu, Cheng, Yu, Li, Bo

Volltext bestellen

EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage von Liao, Zeyi, Mo, Lingbo, Xu, Chejian, Kang, Mintong, Zhang, Jiawei, Xiao, Chaowei, Tian, Yuan, Li, Bo, Sun, Huan

Volltext bestellen

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles von Zhang, Jiawei, Xu, Chejian, Li, Bo

Volltext

Copy Motion From One to Another: Fake Motion Video Generation von Liu, Zhenguang, Wu, Sifan, Xu, Chejian, Wang, Xiang, Zhu, Lei, Wu, Shuang, Feng, Fuli

Volltext bestellen

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks von Wu, Fan, Li, Linyi, Xu, Chejian, Zhang, Huan, Kailkhura, Bhavya, Kenthapadi, Krishnaram, Zhao, Ding, Li, Bo

Volltext bestellen

A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective von Ding, Wenhao, Xu, Chejian, Arief, Mansur, Lin, Haohong, Li, Bo, Zhao, Ding

Volltext bestellen

COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks von Huang, Zijian, Chu, Wenda, Li, Linyi, Xu, Chejian, Li, Bo

Volltext

SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles von Xu, Chejian, Ding, Wenhao, Lyu, Weijie, Liu, Zuxin, Wang, Shuai, He, Yihan, Hu, Hanjiang, Zhao, Ding, Li, Bo

Volltext bestellen

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities von Xu, Peng, Wei, Ping, Wu, Xianchao, Xu, Chejian, Liu, Zihan, Shoeybi, Mohammad, Catanzaro, Bryan

Volltext

Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models von Wang, Boxin, Xu, Chejian, Wang, Shuohang, Gan, Zhe, Cheng, Yu, Gao, Jianfeng, Awadallah, Ahmed Hassan, Li, Bo

Volltext bestellen

AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents von Xu, Chejian, Kang, Mintong, Zhang, Jiawei, Liao, Zeyi, Mo, Lingbo, Yuan, Mengqi, Sun, Huan, Li, Bo

Volltext

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models von Wang, Boxin, Chen, Weixin, Pei, Hengzhi, Xie, Chulin, Kang, Mintong, Zhang, Chenhui, Xu, Chejian, Xiong, Zidi, Dutta, Ritik, Schaeffer, Rylan, Truong, Sang T, Arora, Simran, Mazeika, Mantas, Hendrycks, Dan, Lin, Zinan, Cheng, Yu, Koyejo, Sanmi, Song, Dawn, Li, Bo

Volltext bestellen