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 161–180 of 1,455 papers
Clear filtersYujie Ma, Jialin Rong, Chenxi Yang +4 more
Large Language Models(LLMs) have been actively integrated into modern software systems as critical components. LLM-in-the-loop vulnerabilities, where...
Junjie Mu, Qiongxiu Li
Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because raw data remain local. As a result,...
Jiachen Qian
Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present...
Yongwoo Kim, Sojung An, Yunjin Park +8 more
Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and...
Xiang Fang, Wanlong Fang
Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms,...
Cihan Xiao, Yiwen Shao, Chenxing Li +5 more
Audio and omni-modal large language models exhibit impressive cross-modal reasoning capabilities. However, applying standard reinforcement learning...
Arthur Renard, Franck Gabriel, Valentin Hartmann +1 more
We present Frost Training, a method for improving Monte Carlo-based policy optimization for a large family of LLM-as-a-judge tasks called...
Syed Huma Shah
Modern retrieval-augmented generation(RAG) deployments increasingly rely on caching to reduce token cost and time-to-first-token(TTFT). Prefix-level...
Md Hafizur Rahman, Zafaryab Haider, Tanzim Mahfuz +1 more
Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves...
Xuan Luo, Yue Wang, Geng Tu +2 more
In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal...
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...
Wajdi Zaghouani, Kholoud K. Aldous, Isra Fejzullaj
Safety evaluation of Large Language Models (LLMs) has largely focused on high-resource languages, leaving low-resource languages critically...
Yunbo Long, Haolang Zhao, Lukas Beckenbauer +2 more
Post-trained LLMs are often optimized to align responses with human preferences, making them safe, polite, and conversationally appropriate. In...
Zhe Yu, Wenpeng Xing, Gaolei Li +4 more
Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable to Confundo-style poisoning where...
Haodong Zhao, Tianyi Xu, Tianhang Zhao +2 more
Fine-tuning Large Language Models with untrusted data exposes models to backdoor attacks, where poisoned samples cause targeted misbehavior. Existing...
Hwiwon Lee, Jiawei Liu, Dongjun Kim +3 more
Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation....
Peiran Wang, Ying Li, Yuan Tian
LLM-based agents are increasingly deployed in high-stakes scenarios such as email management, financial transactions, and code execution, where they...
Ujwal Kumar, Arth Singh, Hershraj Niranjani +5 more
Frontier LLM agents engage in blackmail, sabotage, and document leaks under goal conflicts in agentic settings, exposing limitations of alignment...
Sandeep Kumar, Virginia Smith, Chhavi Yadav
Direct Preference Optimisation (DPO) is widely used for safety alignment in large language models. However, prior work shows it is brittle and...
David Košťál, Martin Jureček
We present a dataset of adversarial malware samples derived from the public RawMal-TF collection of real-world malware binaries. Using a suite of...
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