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 81–100 of 610 papers
Clear filtersReshabh K Sharma, Linxi Jiang, Shuo Chen +1 more
A language model agent acts through the tools it is given. The data it reads while working on a task can redirect what it does with those tools. A...
Brandon Bauer, Matthew Whalen, Kenji Watanabe +4 more
Artificial-intelligence (AI) agents are beginning to enter experimental laboratories, automating experiments and accelerating scientific discovery....
Francesca Medda, Hui Gong
Dementia care increasingly involves connected sensors, medication devices, electronic records, and assistive technologies. Interoperability can...
Chao Huang, Meng Tong, Kejiang Chen
While multimodal large language models (MLLMs) enable a wide range of image-text reasoning tasks, recent incidents indicate that they are vulnerable...
Bijied Brahimi, Vincent Cohadon, Gabriel Glazman +3 more
Static malware detection for Windows Portable Executable files demands a careful balance between detection effectiveness, computational efficiency,...
Elizabeth Pavlova, Hidenori Tanaka
Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid...
Jean-Charles Noirot Ferrand, David Adei, Anders Møller +1 more
Malicious npm package detection tools now leverage LLMs' semantic understanding of source code to detect malicious intent at scale. This capability...
Youjia Wang, Lin Xu, Yang Sun +3 more
Safety alignment teaches large language models (LLMs) to recognize harmful requests and reject risky instructions. Yet aligned models can fail when...
Rahul Dev T Y, Hiran V Nath
LLM-powered autonomous agents are transforming the penetration testing space with dynamic, multi-step offensive security workflows that require...
Aashiq Muhamed, Mona T. Diab, Virginia Smith
Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and...
Natalie Collina, Surbhi Goel, Aaron Roth +1 more
Long-running AI agents create a control problem: each action they take changes the state, which in turn affects the trajectory of future actions. If...
Guo Fuzheng
Retrieval-augmented generation (RAG) grounds a language model's answers on retrieved external knowledge and returns each answer with citations that...
Simona Boboila, Xavier Cadet, Edward Koh +4 more
Cyber attacks are increasingly automated, narrowing the time available for human analysts to detect, reason about, and respond to intrusions. Large...
Rui Wen, Ahmed Salem, Andrew Paverd +2 more
Large language models are often fine-tuned, shared, or downloaded from third parties, so a deployed model may carry a hidden backdoor that behaves...
Muhammad Fahad Bashir, Muhammad Afzal
With the existing digital mental health tools specifically developed for Western settings, Pakistani students are exposed to a uniquely compounded...
Vikash Singh, Debargha Ganguly, Aman Goel +5 more
Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal...
Ivana Clairine Irsan, Ratnadira Widyasari, Huihui Huang +6 more
Static analysis remains a cornerstone of software security, yet the effectiveness of tools such as CodeQL is often limited by the substantial manual...
Hanyi Zhou, Chenyang Li, Yuanzhe Pang +3 more
Trusted Execution Environments (TEEs) offer a promising mechanism for safeguarding the intellectual property of on-device Large Language Models...
Mingyu Ma, Yuxin Wu, Jingbo Wang +3 more
Large Language Models (LLMs) are increasingly deployed with hierarchical instructions, yet they remain vulnerable to conflicts in which user...
Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +2 more
Automatic safety judges -- systems such as Llama Guard or a GPT-4o grading prompt that decide whether a model's reply is harmful -- produce the...
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