2,077+ academic papers on AI security, attacks, and defenses
Showing 21–40 of 522 papers
Clear filtersZhenlin 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...
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...
Chenlong Yin, Runpeng Geng, Yanting Wang +1 more
Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been...
Zheng Gao, Yifan Yang, Xiaoyu Li +4 more
Watermarking the initial noise of diffusion models has emerged as a promising approach for image provenance, but content-independent noise patterns...
Sihao Ding
We introduce Colluding LoRA (CoLoRA), an attack in which each adapter appears benign and plausibly functional in isolation, yet their linear...
Darren Cheng, Wen-Kwang Tsao
Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject...
Xinhai Wang, Shaopeng Fu, Shu Yang +3 more
Suffix jailbreak attacks serve as a systematic method for red-teaming Large Language Models (LLMs) but suffer from prohibitive computational costs,...
Davi Bonetto
State Space Models (SSMs) such as Mamba achieve linear-time sequence processing through input-dependent recurrence, but this mechanism introduces a...
Alexandre Le Mercier, Thomas Demeester, Chris Develder
State space models (SSMs) like Mamba have gained significant traction as efficient alternatives to Transformers, achieving linear complexity while...
J Alex Corll
Prompt injection defenses are often framed as semantic understanding problems and delegated to increasingly large neural detectors. For the first...
Indranil Halder, Annesya Banerjee, Cengiz Pehlevan
Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial...
Nasim Soltani, Shayan Nejadshamsi, Zakaria Abou El Houda +4 more
Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network...
Scott Thornton
Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge sources but introduce new attack surfaces...
Nanzi Yang, Weiheng Bai, Kangjie Lu
The Model Context Protocol (MCP) is a recently proposed interoperability standard that unifies how AI agents connect with external tools and data...
Ailiya Borjigin, Igor Stadnyk, Ben Bilski +2 more
OpenClaw-style agent stacks turn language into privileged execution: LLM intents flow through tool interception, policy gates, and a local executor....
Fan Yang
The widespread adoption of thinking mode in large language models (LLMs) has significantly enhanced complex task processing capabilities while...
Quanchen Zou, Moyang Chen, Zonghao Ying +6 more
Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit...
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