2,560+ academic papers on AI security, attacks, and defenses
Showing 321–340 of 725 papers
Clear filtersMitchell 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...
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...
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....
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...
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...
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...
Somnath Banerjee
The overarching research direction of this work is the development of a ''Responsible Intelligence'' framework designed to reconcile the immense...
Yuqi Jia, Ruiqi Wang, Xilong Wang +2 more
Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one....
Ruomeng Ding, Yifei Pang, He Sun +3 more
Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language...
Weiming Song, Xuan Xie, Ruiping Yin
Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses...
Akshat Naik, Jay Culligan, Yarin Gal +4 more
As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a...
Yiran Gao, Kim Hammar, Tao Li
Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively...
Alfous Tim, Kuniyilh Simi D
The Internet of Things (IoT) systems increasingly depend on continual learning to adapt to non-stationary environments. These environments can...
Osama Zafar, Shaojie Zhan, Tianxi Ji +1 more
In recent years, the widespread adoption of Machine Learning as a Service (MLaaS), particularly in sensitive environments, has raised considerable...
Oguzhan Baser, Elahe Sadeghi, Eric Wang +5 more
Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM...
Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3 more
Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based...
Dong Yan, Jian Liang, Ran He +1 more
Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text...
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