AI Threat Alert indexes 3,023+ peer-reviewed and preprint papers on AI/ML security — covering adversarial attacks, model defenses, red-teaming benchmarks, surveys, and security tooling. Papers are sourced from arXiv, classified by type and by relevance to real-world threats, and cross-referenced with the CVEs and incidents they relate to.
Showing 2661–2680 of 3,023 papers
Alireza Heshmati, Saman Soleimani Roudi, Sajjad Amini +2 more
Existing adversarial attacks often neglect perturbation sparsity, limiting their ability to model structural changes and to explain how deep neural...
Yiyang Huang, Liang Shi, Yitian Zhang +2 more
Large Vision-Language Models (LVLMs) excel in diverse cross-modal tasks. However, object hallucination, where models produce plausible but inaccurate...
Xiaofan Li, Xing Gao
The Model Context Protocol (MCP) is an emerging open standard that enables AI-powered applications to interact with external tools through structured...
Guangyu Lin, Li Lin, Christina P. Walker +2 more
The rapid proliferation of AI-generated content, driven by advances in generative adversarial networks, diffusion models, and multimodal large...
Dimitris Stefanopoulos, Andreas Voskou
This report presents the winning solution for Task 1 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery...
David Peer, Sebastian Stabinger
Large Language Models (LLMs) have demonstrated impressive capabilities, yet their deployment in high-stakes domains is hindered by inherent...
Shuai Li, Kejiang Chen, Jun Jiang +5 more
Large Language Models (LLMs) have demonstrated remarkable capabilities, but their training requires extensive data and computational resources,...
Mohammad Abdul Rehman, Syed Imad Ali Shah, Abbas Anwar +2 more
The remarkable capabilities of Large Language Models (LLMs) in natural language understanding and generation have sparked interest in their potential...
Sarah Egler, John Schulman, Nicholas Carlini
Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that...
Yang Feng, Xudong Pan
Malicious agents pose significant threats to the reliability and decision-making capabilities of Multi-Agent Systems (MAS) powered by Large Language...
Kate Glazko, Jennifer Mankoff
Generative AI risks such as bias and lack of representation impact people who do not interact directly with GAI systems, but whose content does:...
Owais Makroo, Siva Rajesh Kasa, Sumegh Roychowdhury +4 more
Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a...
Shiwen Ou, Yuwei Li, Lu Yu +6 more
Deep learning (DL) frameworks serve as the backbone for a wide range of artificial intelligence applications. However, bugs within DL frameworks can...
Eduard Andrei Cristea, Petter Molnes, Jingyue Li
Malicious software attacks are having an increasingly significant economic impact. Commercial malware detection software can be costly, and tools...
Yao Huang, Yitong Sun, Yichi Zhang +3 more
Despite the remarkable advances of Large Language Models (LLMs) across diverse cognitive tasks, the rapid enhancement of these capabilities also...
Yuexiao Liu, Lijun Li, Xingjun Wang +1 more
Recent advancements in Reinforcement Learning with Verifiable Rewards (RLVR) have gained significant attention due to their objective and verifiable...
Muslim Chochlov, Gul Aftab Ahmed, James Vincent Patten +4 more
Source code clones pose risks ranging from intellectual property violations to unintended vulnerabilities. Effective and efficient scalable clone...
Hanbin Hong, Shuya Feng, Nima Naderloui +6 more
Large Language Models (LLMs) have rapidly become integral to real-world applications, powering services across diverse sectors. However, their...
Shuang Liang, Zhihao Xu, Jialing Tao +2 more
Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To...
Luca Belli, Kate Bentley, Will Alexander +5 more
We introduce VERA-MH (Validation of Ethical and Responsible AI in Mental Health), an automated evaluation of the safety of AI chatbots used in mental...
AI security research studies how AI and machine-learning systems can be attacked and defended — covering adversarial examples, prompt injection, model poisoning, training-data extraction, and the mitigations against them. AI Threat Alert curates this research from academic sources so security teams can track the threats behind emerging AI risks.
AI Threat Alert indexes 3,023+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Papers are sourced from arXiv, then classified by type and by relevance to real-world AI/ML threats, and cross-referenced with the CVEs and incidents they relate to.
Coverage spans adversarial attacks, model and system defenses, red-teaming benchmarks, literature surveys, and security tooling for LLMs, ML libraries, AI agents, and inference pipelines.
Every paper is filtered for AI security relevance and linked to the vulnerabilities, vendors, and incidents it relates to, so the research connects directly to operational threat intelligence.
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