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 101–120 of 1,229 papers
Clear filtersVarun Gumma, Navonil Majumdar, Soujanya Poria
The rapid proliferation of Large Language Models (LLMs) necessitates reliable watermarking techniques to identify AI-generated text and ensure...
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...
Hui Zhang, Yachao Yuan, Jiayun Wang +3 more
Fine-tuning-as-a-service enables users to adapt aligned large language models (LLMs) to specialized tasks, but malicious fine-tuning can erode...
Alexi Canesse, Mathis Le Bail, Maël Jenny +3 more
An LLM safety patch can pass a benchmark while still being a poor repair. This risk is especially acute for jailbreak repairs, where the goal is to...
Dang K Le, Wenxuan Shi, Xinyu Xing
Large language models (LLMs) have shown strong potential for automated vulnerability patching, but current benchmarks can substantially distort...
Bojun Yang, Haochen Zhou, Zhifang Zhang +3 more
Large vision-language models (LVLMs) are increasingly deployed in safety-critical applications, yet they remain vulnerable to backdoor attacks....
Zhuchenyang Liu, Yao Zhang, Yu Xiao
Prevailing multi-vector visual document retrievers store each page as about a thousand patch vectors, often in vector databases run by a third party....
Nikolaos Kekatos, Stylianos Basagiannis, Marinelio Chintri +5 more
Guardrails for tool-using LLM agents are usually application-specific rules, which makes multi-step, data-dependent safety policies hard to specify,...
Shuailong Wang, Xinyu Lyu, Shengming Yuan +3 more
Token-Pruning accelerates Vision-Language Models by removing redundant visual tokens, yet its safety implications remain underexplored. In this work,...
Tianruo Rose Xu, Jiawei Ren, Yichi Yang +2 more
Rapid progress in AI agents has brought growing attention to agent safety, with extensive evaluation focused on digital environments. As agents move...
Pavan Maddula
Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while models in real-world deployment...
Yichi Zhang, Zhiqi Wang, Neil Gong +1 more
Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model,...
Niveen O. Jaffal, Ahmet Yuksel, David Mohaisen
Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content. We introduce RAG-PIBench, a...
Hao Sun, Yibin Yao, Chaohai Xie +1 more
Dynamic Application Security Testing (DAST) scanners achieve high recall but also produce a large number of false positives, resulting in substantial...
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...
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...
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...
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...
Hao Sun, Yibin Yao, Chaohai Xie +1 more
Computer vision services delivered through Web interfaces and APIs process textual requests for image-resource acquisition, inference-task...
Junle Chen, Wei Chen, Zhengjun Huang +5 more
When a large language model handles a multi-turn task and a user proposes a change but ultimately rejects it, the model should continue as if nothing...
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