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 61–80 of 388 papers
Clear filtersWilliam Guanting Li, Alsharif Abuadbba, Kristen Moore +1 more
Penetration testing is essential to securing modern web infrastructures, yet traditional manual methods struggle to keep pace with their scale and...
Tianyun Zhang, Zhen Yang, Haozhao Wang +2 more
Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods...
Xiang Chen, Yuxian Dong, Chao Li +6 more
Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared...
Shahnewaz Karim Sakib, Swati Kar, Anindya Bijoy Das
Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks...
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...
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...
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...
Kaixiang Wang, Jiong Lou, Zhaojiacheng Zhou +1 more
Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce...
Xin Wang, Yixu Wang, Jiaming Zhang +6 more
Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to...
William Lugoloobi, Samuelle Marro, Jabez Magomere +2 more
As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model...
Yejin Lee, Yo-Sub Han
Diffusion Language Models (DLMs) provide a promising alternative to autoregressive language models by generating text through iterative denoising and...
Nirav Diwan, Han Wang, Berkcan Kapusuzoglu +6 more
Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code...
Olga Sorokoletova, Francesco Giarrusso, Giacomo De Luca +6 more
Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential....
Pranshav Gajjar, Vijay K Shah
This position paper argues that to achieve Level 5 autonomous 6G networks, the next generation of Artificial Intelligence in Radio Access Networks...
Youssef Zaazou, Mark Thomas
Vision-language models (VLMs), such as CLIP and SigLIP 2, are widely used for image classification, yet their vision encoders remain vulnerable to...
Ben Kereopa-Yorke, Guillermo Diaz, Holly Wright +3 more
We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use...
Li Lixing
Modern large language models (LLMs) rely on system prompts to establish behavioral constraints and safety rules. Standard causal self-attention...
Isaac David, Arthur Gervais
Security updates create a short but important window in which defenders and attackers can compare vulnerable and patched software. Yet in many...
Samuel Korn
Retrieval-Augmented Generation (RAG) systems are vulnerable to knowledge base poisoning, yet existing attacks have been evaluated almost exclusively...
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