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 381–400 of 3,023 papers
Leitao Yuan, Qinghua Mao, Daizong Liu +5 more
Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where perturbations optimized on open-source surrogate...
Laura Jiang, Reza Ryan, Qian Li +1 more
Single-turn safety evaluation is a poor proxy for real fraud defense, where attackers escalate across multiple rounds. This paper evaluates fraud...
Amit Roth, Ankur Samanta, Matan Halevy +2 more
Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking,...
Jiachen Ma, Jiawen Zhang, Xiangtian Li +3 more
While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that...
Yifei Wang, Tianlin Li, Xiaohan Zhang +3 more
Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs....
Yong Jin Chun, Iftekhar Ahmed
Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse...
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...
Chengcai Gao, Zhihong Sun, Xiaochuan Shi +2 more
The growing adoption of Retrieval-Augmented Generation (RAG) has led to a rise in adversarial attacks. Existing defenses, relying on semantic...
Mohammed Alshaalan, Miguel R. D. Rodrigues
Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed...
Florian A. D. Burnat, Brittany I. Davidson
Multi-tenant retrieval-augmented generation (RAG) services advertise per-account differential privacy as the operative leakage boundary: each...
Isaac David, Arthur Gervais
Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents?...
Yasmine Hayder
Knowledge Graphs (KGs) are a powerful representation of linked data, offering flexibility, semantic richness, and support for knowledge enrichment...
Zheng Lin, Zhenxing Niu, Haoxuan Ji +2 more
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning...
Paul Wang, Jade Garcia-Bourrée, Anne-Marie Kermarrec +1 more
As jailbreaks, adversarially crafted inputs that bypass safety constraints, continue to be discovered in Large Language Models, practitioners...
Doguhuan Yeke, Yanming Zhou, Leo Y. Lin +3 more
Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical...
Hongyu Cai, Arjun Arunasalam, Yiming Liang +2 more
Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model...
Quanxing Xu, Yuhao Tian, Ling Zhou +4 more
Visual Question Answering (VQA), as the representative multimodal task, serves as a key benchmark for evaluating the reasoning capabilities of...
Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou +3 more
Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains...
Xiaoyan Ma, Seohyun Lee, Taejoon Kim +1 more
Over-the-air federated learning (OTA-FL) improves communication efficiency by exploiting the superposition property of wireless channels, but this...
Tobias Braun, Jonas Henry Grebe, Hossein Shakibania +2 more
Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared...
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