2,529+ academic papers on AI security, attacks, and defenses
Showing 101–120 of 440 papers
Clear filtersJinhu Qi, Yifan Li, Minghao Zhao +4 more
As agentic AI systems move beyond static question answering into open-ended, tool-augmented, and multi-step real-world workflows, their increased...
Ivan Lopez, Selin S. Everett, Bryan J. Bunning +10 more
Large language models (LLMs) are entering clinician workflows, yet evaluations rarely measure how clinician reasoning shapes model behavior during...
Arjun Chakraborty, Sandra Ho, Adam Cook +1 more
CTI-REALM (Cyber Threat Real World Evaluation and LLM Benchmarking) is a benchmark designed to evaluate AI agents' ability to interpret cyber threat...
Zhifang Zhang, Bojun Yang, Shuo He +5 more
Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where...
Ninghui Li, Kaiyuan Zhang, Kyle Polley +1 more
This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and...
Junjie Chu, Yiting Qu, Ye Leng +4 more
Large Language Models (LLMs) are increasingly trained to align with human values, primarily focusing on task level, i.e., refusing to execute...
Qizhi Chen, Chao Qi, Yihong Huang +5 more
Graph-based Retrieval-Augmented Generation (GraphRAG) constructs the Knowledge Graph (KG) from external databases to enhance the timeliness and...
Marc Damie, Murat Bilgehan Ertan, Domenico Essoussi +3 more
With their increasing capabilities, Large Language Models (LLMs) are now used across many industries. They have become useful tools for software...
Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu +10 more
Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete,...
Manit Baser, Alperen Yildiz, Dinil Mon Divakaran +1 more
The static knowledge representations of large language models (LLMs) inevitably become outdated or incorrect over time. While model-editing...
Amir Al-Maamari
Large Language Models (LLMs) show promise for Automated Program Repair (APR), yet their effectiveness on security vulnerabilities remains poorly...
Chenxi Li, Xianggan Liu, Dake Shen +9 more
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that...
Yige Li, Wei Zhao, Zhe Li +6 more
Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same...
Yuxu Ge
Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and...
Xiaoguang Li, Hanyi Wang, Yaowei Huang +6 more
Shuffler-based differential privacy (shuffle-DP) is a privacy paradigm providing high utility by involving a shuffler to permute noisy report from...
Yuchen Shi, Huajie Chen, Heng Xu +6 more
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources....
Kelly L Vomo-Donfack, Adryel Hoszu, Grégory Ginot +1 more
Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions...
Jiaxun Guo, Ziyuan Yang, Mengyu Sun +3 more
The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale. While...
Maheep Chaudhary
Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit...
Aradhye Agarwal, Gurdit Siyan, Yash Pandya +3 more
Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon...
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