2,077+ academic papers on AI security, attacks, and defenses
Showing 1–20 of 178 papers
Clear filtersRui Yang Tan, Yujia Hu, Roy Ka-Wei Lee
Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually...
Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg +1 more
Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on...
Shawn Li, Yue Zhao
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete...
Carlos Hinojosa, Clemens Grange, Bernard Ghanem
Vision-language models (VLMs) are increasingly deployed in real-world and embodied settings where safety decisions depend on visual context. However,...
Ce Zhang, Jinxi He, Junyi He +2 more
Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability...
Zhenheng Tang, Xiang Liu, Qian Wang +3 more
As Large Language Models (LLMs) become more powerful and autonomous, they increasingly face conflicts and dilemmas in many scenarios. We first...
Vanshaj Khattar, Md Rafi ur Rashid, Moumita Choudhury +4 more
Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the...
Yewon Han, Yumin Seol, EunGyung Kong +2 more
Existing jailbreak defence frameworks for Large Vision-Language Models often suffer from a safety utility tradeoff, where strengthening safety...
Suvadeep Hajra, Palash Nandi, Tanmoy Chakraborty
Safety tuning through supervised fine-tuning and reinforcement learning from human feedback has substantially improved the robustness of large...
Pengcheng Li, Jie Zhang, Tianwei Zhang +5 more
Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although...
Matthew Butler, Yi Fan, Christos Faloutsos
The proposed method (FraudFox) provides solutions to adversarial attacks in a resource constrained environment. We focus on questions like the...
Zonghao Ying, Xiao Yang, Siyang Wu +7 more
The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape....
Xinhao Deng, Yixiang Zhang, Jiaqing Wu +15 more
Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks....
Zhiyu Xue, Zimo Qi, Guangliang Liu +2 more
Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal...
Harry Owiredu-Ashley
Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to capture...
Bo Jiang
Knowledge distillation from proprietary LLM APIs poses a growing threat to model providers, yet defenses against this attack remain fragmented and...
Sumit Ranjan, Sugandha Sharma, Ubaid Abbas +1 more
Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt...
Xisen Jin, Michael Duan, Qin Lin +4 more
As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces...
Jinman Wu, Yi Xie, Shen Lin +2 more
Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the...
Ved Sriraman, Adam Block
Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a...
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