2,583+ academic papers on AI security, attacks, and defenses
Showing 781–800 of 2,583 papers
Qingxiao Xu, Ze Sheng, Zhicheng Chen +1 more
Large language models (LLMs) have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into...
Mingcheng Jiang, Jiancheng Huang, Jiangfei Wang +5 more
Static Application Security Testing (SAST) tools often suffer from high false positive rates, leading to alert fatigue that consumes valuable...
Huajie Chen, Tianqing Zhu, Yuchen Zhong +7 more
Dataset distillation compresses a large real dataset into a small synthetic one, enabling models trained on the synthetic data to achieve performance...
Jiayao Wang, Yiping Zhang, Mohammad Maruf Hasan +5 more
Self-supervised diffusion models learn high-quality visual representations via latent space denoising. However, their representation layer poses a...
Martin Odersky, Yaoyu Zhao, Yichen Xu +2 more
AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause...
Oluseyi Olukola, Nick Rahimi
Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both...
Hsin Lin, Yan-Lun Chen, Ren-Hung Hwang +1 more
Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually...
Zihang Wang, Xu Li, Benwu Wang +7 more
Explainability and transparent decision-making are essential for the safe deployment of autonomous driving systems. Scene captioning summarizes...
Yilian Liu, Xiaojun Jia, Guoshun Nan +6 more
Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful...
Ming Wen, Kun Yang, Xin Chen +4 more
Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as...
Swapnil Parekh
Image captioning models are encoder-decoder architectures trained on large-scale image-text datasets, making them susceptible to adversarial attacks....
Haodong Zhao, Jinming Hu, Zhaomin Wu +7 more
Federated Instruction Tuning (FIT) enables collaborative instruction tuning of large language models across multiple organizations (clients) in a...
Jingyuan Xie, Wenjie Wang, Ji Wu +1 more
Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly...
Linxi Jiang, Zhijie Liu, Haotian Luo +1 more
Browser-use agents are widely used for everyday tasks. They enable automated interaction with web pages through structured DOM based interfaces or...
Yijun Yu
Agentic AI systems exhibit numerous crosscutting concerns -- security, observability, cost management, fault tolerance -- that are poorly modularized...
Chang Xue, Fang Liu, Jiaye Wang +2 more
Decentralized financial platforms rely heavily on Web of Trust reputation systems to mitigate counterparty risk in the absence of centralized...
Om Tailor
Colluding language-model agents can hide coordination in messages that remain policy-compliant at the surface level. We present CLBC, a protocol...
Rahul Baxi
AI agents are increasingly granted economic agency (executing trades, managing budgets, negotiating contracts, and spawning sub-agents), yet current...
Yashas Hariprasad, Subhash Gurappa, Sundararaj S. Iyengar +3 more
The Forensics Investigations Network in Digital Sciences (FINDS) Research Center of Excellence (CoE), funded by the U.S. Army Research Laboratory,...
Reva Schwartz, Carina Westling, Morgan Briggs +12 more
This paper proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-centric performance metrics and AI's...
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