2,560+ academic papers on AI security, attacks, and defenses
Showing 341–360 of 2,560 papers
Nicolás E. Díaz Ferreyra, Monika Swetha Gurupathi, Zadia Codabux +2 more
Generative Artificial Intelligence (GenAI) has become a central component of many development tools (e.g., GitHub Copilot) that support software...
Yuming Xu, Mingtao Zhang, Zhuohan Ge +5 more
Retrieval-augmented generation (RAG) significantly enhances large language models (LLMs) but introduces novel security risks through external...
Weiwei Qi, Zefeng Wu, Tianhang Zheng +4 more
Ensuring Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of...
Labani Halder, Payel Sadhukhan, Sarbani Palit
Ensuring reliability in adversarial settings necessitates treating privacy as a foundational component of data-driven systems. While differential...
Ponnampalam Pirapuraj, Tamal Mondal, Sharanya Gupta +3 more
Application Programming Interfaces (APIs) are crucial to software development, enabling integration of existing systems with new applications by...
Wenpeng Xing, Moran Fang, Guangtai Wang +2 more
While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety...
Wenkui Yang, Chao Jin, Haisu Zhu +7 more
Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is...
Rui Zhang, Hongwei Li, Yun Shen +6 more
The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve...
Cheng Liu, Xiaolei Liu, Xingyu Li +2 more
Existing jailbreak defense paradigms primarily rely on static detection of prompts, outputs, or internal states, often neglecting the dynamic...
Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt +1 more
In language model interpretability research, \textbf{circuit tracing} aims to identify which internal features causally contributed to a particular...
Mehrdad Rostamzadeh, Sidhant Narula, Nahom Birhan +2 more
The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding...
Hengkai Ye, Zhechang Zhang, Jinyuan Jia +1 more
Large language models (LLMs) increasingly rely on external tools to perform time-sensitive tasks and real-world actions. While tool integration...
Yu Liang, Liangxin Liu, Longzheng Wang +5 more
Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering...
Hanyi Liu, Zhonghao Jiu, Minghao Wang +2 more
Implicit artistic influence, although visually plausible, is often undocumented and thus poses a historically constrained attribution problem:...
Yuanhang Li
Operating LEO mega-constellations requires translating high-level operator intents ("reroute financial traffic away from polar links under 80 ms")...
Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1 more
As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to...
Luat Do, Jiao Yin, Jinli Cao +1 more
Software vulnerabilities continue to pose significant threats to modern information systems, requiring a timely and accurate risk assessment. Public...
Zhiheng Li, Zongyang Ma, Yuntong Pan +8 more
Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a...
Zhiheng Li, Zongyang Ma, Yuntong Pan +8 more
Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a...
Simon Calderon, Niklas Johansson, Onur Günlü
Ensuring ciphertext indistinguishability is fundamental to cryptographic security, but empirically validating this property in real implementations...
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert