2,077+ academic papers on AI security, attacks, and defenses
Showing 41–60 of 102 papers
Clear filtersDavi 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...
Sarbartha Banerjee, Prateek Sahu, Anjo Vahldiek-Oberwagner +2 more
Rapid progress in generative AI has given rise to Compound AI systems - pipelines comprised of multiple large language models (LLM), software tools...
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...
Xiangwen Wang, Ananth Balashankar, Varun Chandrasekaran
Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with...
Fabrizio Dimino, Bhaskarjit Sarmah, Stefano Pasquali
The rapid adoption of large language models (LLMs) in financial services introduces new operational, regulatory, and security risks. Yet most...
Yu He, Haozhe Zhu, Yiming Li +4 more
LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack...
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...
Pratyay Kumar, Abu Saleh Md Tayeen, Satyajayant Misra +4 more
Deep learning (DL)-based Network Intrusion Detection System (NIDS) has demonstrated great promise in detecting malicious network traffic. However,...
David Fernandez, Pedram MohajerAnsari, Amir Salarpour +3 more
Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper...
Junxian Li, Tu Lan, Haozhen Tan +2 more
Modern vision-language-model (VLM) based graphical user interface (GUI) agents are expected not only to execute actions accurately but also to...
Yonghong Deng, Zhen Yang, Ping Jian +3 more
With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety...
Jialai Wang, Ya Wen, Zhongmou Liu +4 more
Targeted bit-flip attacks (BFAs) exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work...
Ondřej Lukáš, Jihoon Shin, Emilia Rivas +6 more
Autonomous offensive agents often fail to transfer beyond the networks on which they are trained. We isolate a minimal but fundamental shift --...
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