AI Threat Alert indexes 4,319+ 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 381–400 of 4,319 papers
Haneen Najjar, Luca Scionis, Haritz Puerto +1 more
AI agents increasingly rely on modular third-party "skills" that are dynamically selected by skill routers to execute complex tasks. While recent...
Weiwei Qi, Chongyu Wang, Tianhang Zheng +5 more
Supervised fine-tuning can substantially improve the downstream utility of large language models (LLMs) but may compromise their safety. Existing...
Yiming Xu, Hongyue Yu, Beihua Yang +8 more
As large language model (LLM) agents become increasingly autonomous, they may pursue task performance through deception, raising concerns about their...
Georgios Koutidis, Nikolaos Kekatos, Marina Korgiala-Karyda +2 more
The EU Cyber Resilience Act (CRA), Regulation (EU) 2024/2847, makes product cybersecurity a lifecycle obligation for products with digital elements...
Yibo Zhang, Tianrong Guan, Liang Lin +3 more
Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric:...
Shailen Smith, Rasmus Torp, Adam Breuer
In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy...
Shaswata Mitra, Raj Patel, Subash Neupane +3 more
LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial content. Current defenses for MAS...
Lizhi Zhang, Xin He, Dianxuan Fu +5 more
Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this...
Zhengyang Zhu, Liming Huang, Runmin Ji +8 more
Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain incompletely characterized....
Hongyu Cao, Yanchi Liu, Kunpeng Liu +5 more
LoRA fine-tuning adapts small language models (SLMs) to heterogeneous instruction data within a low-rank update subspace, making it vulnerable to...
Wonjun Lee, Kyungsik Yang, Gaeun Ji +5 more
LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks...
Ziqun Bao, Xinyu Zhang, Yuchen Shao +1 more
Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of...
Qiusi Zhan, Nian Lyu, Stephanie Ding +3 more
Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker...
Shai Feldman, Yaniv Romano
We evaluate large language models (LLMs) in multi-turn interactions through their time-to-event: the number of interaction steps required to produce...
Krishna Kabra, Constantin Venhoff, Christian Schroeder de Witt
Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring...
Marsalis Gibson, Claire Tomlin, Shankar Sastry
Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive...
Amartya Sanyal
We study mistake bounds for differentially private online learning and online prediction under oblivious realisable adversaries. Online learning...
Abhinav Sudhakar Dubey, Scott Sirri, Vaggos Chatziafratis +1 more
While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important...
Jiaming Qian, Pengyang Zhou, Jiahe Xu +1 more
Adversarial attacks on Large Language Models (LLMs) aim to induce harmful content. However, existing methods suffer from high computational costs or...
Tobias Heldt, Matt Turk, Christoph Landolt +1 more
The release decision for frontier AI systems increasingly relies on cyber capability benchmarks, yet public vulnerability benchmarks can expose...
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 4,319+ 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