Models That Are Interpretable But Not Transparent
Authors: Chudi Zhong, Panyu Chen, Cynthia Rudin | Published: 2025-02-26
Literature Database
Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs
Authors: Shiyu Xiang, Ansen Zhang, Yanfei Cao, Yang Fan, Ronghao Chen | Published: 2025-02-26 | Updated: 2025-05-28
Evaluating Membership Inference Attacks in heterogeneous-data setups
Authors: Bram van Dartel, Marc Damie, Florian Hahn | Published: 2025-02-26 | Updated: 2025-04-28
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
Authors: Hyeonjeong Ha, Qiusi Zhan, Jeonghwan Kim, Dimitrios Bralios, Saikrishna Sanniboina, Nanyun Peng, Kai-Wei Chang, Daniel Kang, Heng Ji | Published: 2025-02-25 | Updated: 2025-10-08
Detecting Benchmark Contamination Through Watermarking
Authors: Tom Sander, Pierre Fernandez, Saeed Mahloujifar, Alain Durmus, Chuan Guo | Published: 2025-02-24 | Updated: 2025-07-21
GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
Authors: Ruixuan Huang, Xunguang Wang, Zongjie Li, Daoyuan Wu, Shuai Wang | Published: 2025-02-24 | Updated: 2025-07-09
Guardians of the Agentic System: Preventing Many Shots Jailbreak with Agentic System
Authors: Saikat Barua, Mostafizur Rahman, Md Jafor Sadek, Rafiul Islam, Shehenaz Khaled, Ahmedul Kabir | Published: 2025-02-23 | Updated: 2025-06-12
Can Indirect Prompt Injection Attacks Be Detected and Removed?
Authors: Yulin Chen, Haoran Li, Yuan Sui, Yufei He, Yue Liu, Yangqiu Song, Bryan Hooi | Published: 2025-02-23
Robustness and Cybersecurity in the EU Artificial Intelligence Act
Authors: Henrik Nolte, Miriam Rateike, Michèle Finck | Published: 2025-02-22 | Updated: 2025-05-28
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
Authors: Ivoline Ngong, Swanand Kadhe, Hao Wang, Keerthiram Murugesan, Justin D. Weisz, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy | Published: 2025-02-22 | Updated: 2025-07-28