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 1–20 of 70 papers
Clear filtersNada Lahjouji, Ashwin Gerard Colaco
Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a...
Jintao Huang, Fengqing Jiang, Radha Poovendran +1 more
We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability...
Thi Huyen Nguyen, Zahra Ahmadi
The rapid growth of scientific submissions has pushed traditional peer review toward its scalability limits, motivating the exploration of large...
Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar +1 more
General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety safeguards remain inadequate...
Junquan Deng, Zhiyu Fan, Ruijie Meng
Recent advances in large language models (LLMs) have enabled vibe coding, an emerging software development paradigm in which users create...
Junquan Deng, Zhiyu Fan, Ruijie Meng
Recent advances in large language models (LLMs) have enabled vibe coding, an emerging software development paradigm in which users create...
Nafiseh Kahani, Masoud Barati, Diana Addae
AI agents now handle personal data through tool use, function calls, and multi turn dialogue, which can create obligations under the General Data...
Yujeong Kwon, Yiyue Zhang, Shakhzod Yuldoshkhujaev +3 more
Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains...
Liran Tal, Johannes Kloos, Arsenii Rudich +2 more
We ran 300 repeated vulnerability-finding scans to measure how repeatable agentic large language model (LLM) security review is on the same...
Xu Yang, Zhizhou Sha, Junbo Li +10 more
As AI-generated reviews move from experimental tools into peer-review infrastructure, most robustness concerns have focused on explicit attacks such...
Vasisht Duddu, Lipeng He, Asim Waheed +1 more
Machine learning (ML) models are susceptible to various security, privacy, and fairness risks. Adversaries with different characteristics (i.e.,...
Yuhan Ma, Stefan Schmid
Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext...
Emre Turan
As LLM agents begin to take real, irreversible actions (shell commands, file edits, deploys), the standard safety pattern is a human-in-the-loop...
Thamilvendhan Munirathinam
Agent-memory frameworks - mem0, Letta/MemGPT, Cognee, Zep/Graphiti, MemoryOS, MemTensor - each ship their own SDK, storage layout, and operational...
Sivana Hamer, Pat Morrison, William Enck +6 more
Software supply chains, while providing immense economic and software development value, are only as strong as their weakest link. Over the past...
Yujie Lin, Kaidi Jia, Jiayao Ma +2 more
Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this...
Huijun Zhou, Xiaohan Zhang, Haozhe Zhang +3 more
The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments...
Richard J. Young, Gregory D. Moody
The evaluation of large language model refusal on malicious-coding tasks now spans at least thirteen publicly released prompt corpora (AdvBench, the...
Julien Piet, Annabella Chow, Yiwei Hou +5 more
ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default...
Yuhao Wu, Tung-Ling Li, Hongliang Liu
Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution....
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