2,529+ academic papers on AI security, attacks, and defenses
Showing 1–20 of 232 papers
Clear filtersBen Kereopa-Yorke, Guillermo Diaz, Holly Wright +3 more
We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use...
Li Lixing
Modern large language models (LLMs) rely on system prompts to establish behavioral constraints and safety rules. Standard causal self-attention...
Isaac David, Arthur Gervais
Security updates create a short but important window in which defenders and attackers can compare vulnerable and patched software. Yet in many...
Samuel Korn
Retrieval-Augmented Generation (RAG) systems are vulnerable to knowledge base poisoning, yet existing attacks have been evaluated almost exclusively...
Yiwei Zhang, Jeremiah Birrell, Reza Ebrahimi +3 more
Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors...
Marco Rando, Samuel Vaiter
Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit...
Jan Dolejš, Martin Jureček, Róbert Lórencz
Modern malware detection pipelines rely on continuous data ingestion and machine learning to counter the high volume of novel threats. This work...
Jie Zhang, Pura Peetathawatchai, Florian Tramèr +1 more
Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and...
Sarthak Choudhary, Atharv Singh Patlan, Nils Palumbo +3 more
We present Sparse Backdoor, a supply-chain attack that plants a \emph{provably undetectable} backdoor in pre-trained image classifiers, including...
Gabriel Hortea, Juan Tapiador
Malware authors have traditionally relied on polymorphic techniques to produce variants in the same malware family, complicating signature-based...
Gabriel Hortea, Juan Tapiador
Malware authors have traditionally relied on polymorphic techniques to produce variants in the same malware family, complicating signature-based...
Ishrith Gowda
Persistent external memory enables LLM agents to maintain context across sessions, yet its security properties remain formally uncharacterized. We...
Divyam Anshumaan, Sarthak Choudhary, Nils Palumbo +1 more
LLM agents release private data across multi-service interactions. Existing prompt sanitizers based on metric differential privacy treat each release...
Mingshuo Liu, Yiwei Zha, Min Chen
Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style...
Purna Sai Garigipati, Onur Ayan, Kishor Chandra Joshi +1 more
Artificial Intelligence (AI) will play an essential role in 6G. It will fundamentally reshape the network architecture itself and drive major changes...
Wenjing Duan, Qi Zhou, Yuanfan Li
Machine-generated text (MGT) detection is critical for regulating online information ecosystems, yet existing detectors often underperform in...
Wenwei Zhao, Xiaowen Li, Yao Liu +1 more
Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients upload manipulated updates to degrade the performance of the...
Jiajia Li, Xiaoyu Wen, Zhongtian Ma +3 more
The growing capabilities of large language models (LLMs) have driven their widespread deployment across diverse domains, even in potentially...
George Fatouros, Georgios Makridis, John Soldatos +18 more
European financial institutions face mounting regulatory pressure while their security operations centres remain constrained not by data or staffing...
Jona te Lintelo, Lichao Wu, Marina Krček +2 more
Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However,...
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