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 141–160 of 2,152 papers
Clear filtersJuann Kim, Minku Kang
Persona vectors are linear directions in the residual-stream activations of LLMs that encode behavioral traits and enable fine-grained control over...
Jerrold Huang, Junwei Quan, Saiyue Lyu +2 more
Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look...
Amman Yusuf, Jiwoo Shin, Ruizhi Deng +3 more
The Safety-Aware Denoiser (SAD) is a recent, training-free, safety-guidance framework for text diffusion models. During inference, SAD steers text...
Arya Fayyazi, Mehdi Kamal, Massoud Pedram
Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact...
Anning Hu, Yangyu Li, Yuqi Huang +2 more
Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as...
Jincheng Ying, Li Wenlin, Wencheng Yang +1 more
White-box neuron pruning has shown that refusal in large language models (LLMs) can depend on a small, removable set of feed-forward (FFN) channels....
Xiuyuan Qi, Yi Wang, Wenjie Wang
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive information, especially when...
Erin Crawley, Hidenori Tanaka
AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to...
Shihab Ahmed, Md Sajidul Islam Sajid, Teryl Taylor +2 more
Malware defenses often remove or isolate suspicious programs as quickly as possible. While effective for containment, this approach can also waste an...
Saisab Sadhu, Shreeyans Arora, Pratinav Seth
Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence that the decision...
Jingnan Zheng, Dongcheng Zhang, Yi Zhang +10 more
Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to...
Edward Chen, Yuntao Du
Unauthorized model distillation, in which a model is trained on the outputs of a proprietary large language model (LLM), is a growing threat to model...
Georgios Milis, Tom Sander, Tomáš Souček +2 more
Watermarking large language models is popular for tracing chatbot and agentic outputs, yet detectors remain unreleased since exposing them could let...
Steve Nouyep, Sébastien Salva, Maxime Puys
Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge through a multi-stage pipeline. While this...
Varun Gumma, Navonil Majumdar, Soujanya Poria
The rapid proliferation of Large Language Models (LLMs) necessitates reliable watermarking techniques to identify AI-generated text and ensure...
Ines Ortega-Fernandez, Mateusz Kowalczyk, Keri Warr
A compromised LLM inference server can leak model weights by encoding payload bits in otherwise plausible token choices. A replay of the same prompt...
Varun Kohli, Lee Bing Cheng, Nur Hazim Ghazali +3 more
Effective source recovery is critical to security applications such as malware analysis, vulnerability assessment, and legacy maintenance. Large...
Min-Young Yu, Tony Kim, Jang Won Choi
Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules, query an LLM verifier per...
Zhankai Ye, Yanning Wang, Yukai Jin +5 more
Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper. We...
William Hackett, Peter Garraghan
AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt injection and jailbreaks....
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