AI Threat Alert indexes 3,092+ 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 601–620 of 3,092 papers
Di Lu, Bo Zhang, Xiyuan Li +5 more
Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including...
Aleksandr Bowkis, Marie Davidsen Buhl, Jacob Pfau +1 more
A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as...
Chengjie Wang, Jingzheng Wu, Xiang Ling +2 more
Large language models (LLMs) are now largely involved in software development workflows, and the code they generate routinely includes third-party...
Leo Linqian Gan, Jeffery Wu, Longyuan Ge +6 more
Autonomous LLM agents face a critical security risk known as workflow hijacking, where attackers subtly alter tool and skill invocations. Existing...
Guoxin Lu, Letian Sha, Qing Wang +4 more
The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constraints on...
Qinfeng Li, Yuntai Bao, Jianghui Hu +5 more
LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property....
Bonan Ruan, Yeqi Fu, Chuqi Zhang +3 more
GitHub Continuous Integration (CI) workflows increasingly integrate Large Language Models (LLMs) to automate review, triage, content generation, and...
Siyuan Li, Aodu Wulianghai, Xi Lin +6 more
The increasing prevalence of Large Language Models (LLMs) in content creation has made distinguishing human-written textual content from...
Huiyu Xu, Zhibo Wang, Wenhui Zhang +4 more
Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to...
Christopher G. Pedraza Pohlenz, Hassan Jalil Hadi, Ali Hassan +1 more
LLMs are increasingly explored for malware analysis; however, current LLM-based malware attribution remains limited by unsupported indicators and...
Md Farhamdur Reza, Richeng Jin, Tianfu Wu +1 more
Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs) transform a harmful query into a concealed multimodal input to...
Xiaomin Li, Andrzej Banburski-Fahey, Jaron Lanier
Auditing language-model outputs often requires more than judging correctness: an auditor may need to identify which source document most likely...
Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim +5 more
Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models,...
Dasol Choi, Eugenia Kim, Jaewon Noh +14 more
Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover,...
Samuel Korn
Retrieval-Augmented Generation (RAG) systems are vulnerable to knowledge base poisoning, yet existing attacks have been evaluated almost exclusively...
Xinjie Shen, Rongzhe Wei, Peizhi Niu +6 more
Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful...
Hoin Jung, Xiaoqian Wang
While Multimodal Large Language Models (MLLMs) are increasingly integrated with Retrieval-Augmented Generation (RAG) to mitigate hallucinations, the...
Fabrice Harel-Canada, Amit Sahai
LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for detection...
Yiwei Zhang, Jeremiah Birrell, Reza Ebrahimi +3 more
Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors...
Marco Rando, Samuel Vaiter
Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit...
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 3,092+ 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