Knowledge Transfer

BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment

Wang, Jiongxiao, Li, Jiazhao, Li, Yiquan, Qi, Xiangyu, Hu, Junjie, Li, Yixuan, McDaniel, Patrick, Chen, Muhao, Li, Bo, Xiao, Chaowei

The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)December 9, 2024

Robust prompt optimization for defending language models against jailbreaking attacks

Zhou, Andy, Bo Li , Haohan Wang

The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)

Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach

Niu, Chaoxi, Pang, Guansong, Chen, Ling, Liu, Bing

The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback

Lang, Leon, Foote, Davis, Russell, Stuart, Dragan, Anca, Jenner, Erik, Emmons, Scott

The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)

Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness

Li, Yiquan, Chen, Zhongzhu, Jin, Kun, Wang, Jiongxiao, Li, Bo, Xiao, Chaowei

The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

Guo, Chengquan, Liu, Xun, Xie, Chulin, Zhou, Andy, Zeng, Yi, Lin, Zinan, Song, Dawn, Li, Bo

The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS) December 9, 2024

Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms

Deng, Chengyuan, Gao, Jie, Lu, Kevin, Luo, Feng, Sun, Hongbin, Xin, Cheng

The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)

Physical ID-Transfer Attacks Against Multi-Object Tracking via Adversarial Trajectory

Wang, Chenyi, Man, Yanmao, Muller, Raymond, Li, Ming, Celik, Z. Berkay, Gerdes, Ryan, Petit, Jonathan

Annual Computer Security Applications Conference (ACSAC), pp. 1–15. Honolulu, HI

DEEPCAPA: Identifying malicious capabilities in Windows malware

Sastha Vasan, Hojjat Aghakhani, S. Ortolani, R. Vasilenko, Ilya Grishchenko, Christopher Kruegel, Giovanni Vigna

In Proc. Annu. Comput. Secur. Appl. Conf. (ACSAC), Dec. 2024, pp. 826–842.December 8, 2024

Enabling Asymptotic Truth Learning in a Social Network

Lu, Kevin, Chong, Jordan, Lu, Matt, Gao, Jie

Proceedings of the 20th Conference on Web and Internet Economics (WINE'24)

Cleangen: Mitigating backdoor attacks for generation tasks in large language models.

Li, Y., Xu, Z., Jiang, F., Niu, L., Sahabandu, D., Ramasubramanian, B., Poovendran, R.

Conference on Empirical Methods in Natural Language Processing (EMNLP), Miami, FL

XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs

Zichen Chen, Jianda Chen, Ambuj K. Singh, Misha Sra

In Proc. Empirical Methods in Natural Language Processing (EMNLP), pp. 7578–7596, Miami, FL November 12-16, 2024November 12, 2024

Graphene: Towards Data-driven Holistic Security Posture Analysis using AI-generated Attack Graphs

Katsis, Charalampos, Jin, Xin, Sang, Fan, Sun, Jiahao, Bertino, Elisa, Kompella, Ramana Rao, Kundu, Ashish

The 10th IEEE International Conference on Collaboration and Internet Computing (CIC) (short version of the paper).

Mix and Match: Characterizing Heterogeneous Human Behavior in AI-assisted Decision Making

Lu, Zhuoran, Mahmood, Syed Hasan Amin, Li, Zhuoyan, Yin, Ming

Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, Pittsburgh, PA.

RoboGuardZ: A Scalable Zero-Shot Framework for Detecting Zero-Day Malware in Robots

Kaur, Upinder, Celik, Z. Berkay, Voyles, Richard M.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Abu Dhai, UAE

RoboCop: A Robust Zero-Day Cyber-Physical Attack Detection Framework for Robots

Kaur, Upinder, Celik, Z. Berkay, Voyles, Richard M.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Abu Dhai, UAE

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data

Zhou, Andy, Xu, Xiaojun, Raghunathan, Ramesh, Lal, Alok, Guan, Xinze, Yu, Bin, Li, Bo

Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security, Salt Lake City, UT

Jatmo: Prompt Injection Defense by Task-Specific Finetuning

Julien Piet, Maha Alrashed, Chawin Sitawarin, Sizhe Chen, Zeming Wei, Elizabeth Sun , Basel Alomair, David Wagner

European Symposium on Research in Computer Security (ESORICS 2024), Bydgoszcz, Poland, September 16, 2024

Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning

D. Wang, A. Antoniades, K.-D. Luong, E. Zhang, M. Kosan, J. Li, A. K. Singh, W. Y. Wang, L. Li

In Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), August, 2024, pp. 2991–3000.

WEBRR: A Forensic System for Replaying and Investigating Web-Based Attacks in the Modern Web

Allen, Joey, Yang, Zheng, XIao, Feng, Landen, Matthew, Perdisci, Roberto, Lee, Wenke

33rd USENIX Security Symposium, Philadelphia, PA

GuideEnricher: Protecting the Anonymity of Ethereum Mixing Service Users with Deep Reinforcement Learning

De Silva, Ravindu, Guo, Wenbo, Ruaro, Nicola, Grishchenko, Ilya, Kruegel, Christopher, Vigna, Giovanni

33rd USENIX Security Symposium (USENIX Security 24), Philadelphia, PennsylvaniaAugust 14, 2024

ACE: A model poisoning attack on contribution evaluation methods in federated learning

Xu, Z., Jiang, F., Niu, L., Jia, J., Li, Bo, Poovendran, Radha

33rd USENIX Security Symposium (USENIX Security 24), Philadelphia, Pennsylvania

Remote Keylogging Attacks in Multi-user VR Applications

Zihao Su, Kunlin Cai, Reuben Beeler, Lukas Dresel, Allan Garcia, Ilya Grishchenko, Yuan Tian, Christopher Kruegel, Giovanni Vigna

33rd USENIX Security Symposium (USENIX Security 24), Philadelphia, PA, August 14-16, 2024
 

SAIN: Improving ICS Attack Detection Sensitivity via State-Aware Invariants

Syed Ghazanfar Abbas, Muslum Ozgur Ozmen, Abdulellah Alsaheel, Arslan Khan,, Z. Berkay Celik, Dongyan Xu

33rd USENIX Security Symposium (USENIX Security 24), Philadelphia, PA, August 14-16, 2024
 

True Attacks, Attack Attempts, or Benign Triggers? An Empirical Measurement of Network Alerts in a Security Operations Center

Limin Yang, Zhi Chen, Chenkai Wang, Zhenning Zhang, Sushruth Booma, Phuong Cao, Constantin Adam, Alex Withers, Zbigniew Kalbarczyk, Ravishankar K. Iyer, Gang Wang

33rd USENIX Security Symposium (USENIX Security 24), Philadelphia, PA, August 14-16, 2024
 

MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training

Jiacheng Li, Ninghui Li, Bruno Ribeiro

33rd USENIX Security Symposium (USENIX Security 24), Philadelphia, PA, August 14-16, 2024

Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models

Hsu, Aliyah R., ; Zhu, James, Wang, Zhichao, Bi, Bin, Mehrotra, Shubham, Pentyala, Shiva K., Tan, Katherine, Mao, Xiang-Bo, Omrani, Roshanak, Chaudhuri, Sougata, Radhakrishnan, Regunathan, Asur, Sitaram, Cheng, Claire Na, Yu, Bin

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL)

Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning

Pasewark, Eric, Montgomery, Kyle, Duan; Kefei, Song, Dawn, Wang, Chenguang

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL)

SafeDecoding: Defending against jailbreak attacks via safety-aware decoding

Xu, Z., Jiang, F., Niu, L., Jia, J., Li, Bo, Poovendran, Radha

Annual Meeting of the Association for Computational Linguistics (ACL) Bangkok, Thailand

ArtPrompt: ASCII art-based jailbreak attacks against aligned LLMs

Jiang, F., Xu, Z., Niu, L., Xiang, Z., Li, Bo, Poovendran, Radha

Annual Meeting of the Association for Computational Linguistics (ACL), Bangkok, Thailand