2,589+ academic papers on AI security, attacks, and defenses
Showing 921–940 of 2,589 papers
Aditi Prabakaran, Priyesh Shukla
Transient objects in casual multi-view captures cause ghosting artifacts in 3D Gaussian Splatting (3DGS) reconstruction. Existing solutions relied on...
Udbhav Prasad, Aniesh Chawla
Cryptographic digests (e.g., MD5, SHA-256) are designed to provide exact identity. Any single-bit change in the input produces a completely different...
Jiajun Xu, Jiageng Mao, Ang Qi +5 more
Vision Language Models (VLMs) are prone to errors, and identifying where these errors occur is critical for ensuring the reliability and safety of AI...
Mitchell Piehl, Zhaohan Xi, Zuobin Xiong +2 more
Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent...
Huijia Lin, Kameron Shahabi, Min Jae Song
Language models now routinely produce text that is difficult to distinguish from human writing, raising the need for robust tools to verify content...
Manuel Cherep, Pranav M R, Pattie Maes +1 more
The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs)....
Chengzhi Hu, Jonas Dornbusch, David Lüdke +2 more
Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant...
David Puertolas Merenciano, Ekaterina Vasyagina, Raghav Dixit +4 more
LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging...
Xander Davies, Giorgi Giglemiani, Edmund Lau +3 more
Frontier LLMs are safeguarded against attempts to extract harmful information via adversarial prompts known as "jailbreaks". Recently, defenders have...
Yohan Lee, Jisoo Jang, Seoyeon Choi +2 more
Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool...
Lukas Struppek, Adam Gleave, Kellin Pelrine
As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on...
In Chong Choi, Jiacheng Zhang, Feng Liu +1 more
Multi-turn jailbreak attacks are effective against text-only large language models (LLMs) by gradually introducing malicious content across turns....
Tianyu Chen, Dongrui Liu, Xia Hu +2 more
Clawdbot is a self-hosted, tool-using personal AI agent with a broad action space spanning local execution and web-mediated workflows, which raises...
Zhenhong Zhou, Yuanhe Zhang, Hongwei Cai +6 more
The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security...
Matic Korun
We propose a geometric taxonomy of large language model hallucinations based on observable signatures in token embedding cluster structure. By...
Xiaojun Jia, Jie Liao, Simeng Qin +5 more
Agent skills are becoming a core abstraction in coding agents, packaging long-form instructions and auxiliary scripts to extend tool-augmented...
Max Fomin
Detecting prompt injection and jailbreak attacks is critical for deploying LLM-based agents safely. As agents increasingly process untrusted data...
Mario Marín Caballero, Miguel Betancourt Alonso, Daniel Díaz-López +3 more
The most valuable asset of any cloud-based organization is data, which is increasingly exposed to sophisticated cyberattacks. Until recently, the...
Edibe Yilmaz, Kahraman Kostas
The integration of large language models (LLMs) into educational processes introduces significant constraints regarding data privacy and reliability,...
Somnath Banerjee
The overarching research direction of this work is the development of a ''Responsible Intelligence'' framework designed to reconcile the immense...
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