2,077+ academic papers on AI security, attacks, and defenses
Showing 381–400 of 2,032 papers
Clear filtersZachary Coalson, Beth Sohler, Aiden Gabriel +1 more
We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches...
Xinhao Deng, Jiaqing Wu, Miao Chen +3 more
Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution...
Arnold Cartagena, Ariane Teixeira
Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that...
Justin Albrethsen, Yash Datta, Kunal Kumar +1 more
While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of...
Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami +1 more
Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight...
Priyaranjan Pattnayak, Sanchari Chowdhuri
Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities...
Simon Lermen, Daniel Paleka, Joshua Swanson +3 more
We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hacker News...
Nils Palumbo, Sarthak Choudhary, Jihye Choi +2 more
LLM-based agents are increasingly being deployed in contexts requiring complex authorization policies: customer service protocols, approval...
Stephan Rabanser, Sayash Kapoor, Peter Kirgis +3 more
AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many...
Adib Sakhawat, Fardeen Sadab
Evaluating the social intelligence of Large Language Models (LLMs) increasingly requires moving beyond static text generation toward dynamic,...
Thomas Michel, Debabrota Basu, Emilie Kaufmann
Modern AI models are not static. They go through multiple updates in their lifecycles. Thus, exploiting the model dynamics to create stronger...
Robert Ranisch, Sabine Salloch
The emergence of agentic AI marks a new phase in the digital transformation of healthcare. Distinct from conventional generative AI, agentic AI...
Doron Shavit
Jailbreak prompts are a practical and evolving threat to large language models (LLMs), particularly in agentic systems that execute tools over...
Yiwen Lu
Federated Learning (FL) enables collaborative model training without exposing clients' private data, and has been widely adopted in privacy-sensitive...
Michael Cunningham
We present a practical system for privacy-aware large language model (LLM) inference that splits a transformer between a trusted local GPU and an...
Philipp Schoenegger, Matt Carlson, Chris Schneider +1 more
Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used....
Nivya Talokar, Ayush K Tarun, Murari Mandal +2 more
LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to...
Johannes Bertram, Jonas Geiping
We introduce NESSiE, the NEceSsary SafEty benchmark for large language models (LLMs). With minimal test cases of information and access security,...
Ahmed Ryan, Ibrahim Khalil, Abdullah Al Jahid +4 more
The prevalence of malicious packages in open-source repositories, such as PyPI, poses a critical threat to the software supply chain. While Large...
Yu Yin, Shuai Wang, Bevan Koopman +1 more
Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within 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