2,077+ academic papers on AI security, attacks, and defenses
Showing 21–40 of 118 papers
Clear filtersKun Wang, Meng Chen, Junhao Wang +6 more
With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious...
Saikat Maiti
Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system...
Zhihua Wei, Qiang Li, Jian Ruan +4 more
Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts...
Hammad Atta, Ken Huang, Kyriakos Rock Lambros +11 more
Agentic LLM systems equipped with persistent memory, RAG pipelines, and external tool connectors face a class of attacks - Logic-layer Prompt Control...
Patrick Levi
Retrieval augmented generation systems have become an integral part of everyday life. Whether in internet search engines, email systems, or service...
Shenao Yan, Shimaa Ahmed, Shan Jin +4 more
Code generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these...
Kushankur Ghosh, Mehar Klair, Kian Kyars +2 more
Provenance graphs model causal system-level interactions from logs, enabling anomaly detectors to learn normal behavior and detect deviations as...
Yong Zou, Haoran Li, Fanxiao Li +5 more
Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of...
Guangsheng Zhang, Huan Tian, Leo Zhang +4 more
Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor...
Deng Liu, Song Chen
Hardware faults, specifically bit-flips in quantized weights, pose a severe reliability threat to Large Language Models (LLMs), often triggering...
Xiaobing Sun, Perry Lam, Shaohua Li +4 more
Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time...
Amira Guesmi, Muhammad Shafique
Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to...
Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28 more
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code...
Zhenlin Xu, Xiaogang Zhu, Yu Yao +2 more
Modern agentic systems allow Large Language Model (LLM) agents to tackle complex tasks through extensive tool usage, forming structured control flows...
Ruyi Zhang, Heng Gao, Songlei Jian +2 more
Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a...
Maël Jenny, Jérémie Dentan, Sonia Vanier +1 more
Most jailbreak techniques for Large Language Models (LLMs) primarily rely on prompt modifications, including paraphrasing, obfuscation, or...
Chongxin Li, Hanzhang Wang, Lian Duan
Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is...
Yiling Tao, Xinran Zheng, Shuo Yang +2 more
While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security...
Zijian Ling, Pingyi Hu, Xiuyong Gao +6 more
Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic...
Md. Abdul Awal, Mrigank Rochan, Chanchal K. Roy
Large language models for code have achieved strong performance across diverse software analytics tasks, yet their real-world adoption remains...
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