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 221–240 of 272 papers
Clear filtersRanjith Krishnamurthy, Oshando Johnson, Goran Piskachev +1 more
Security vulnerabilities often arise unintentionally during development due to a lack of security expertise and code complexity. Traditional tools,...
Zeyuan He, Yupeng Chen, Lang Lin +7 more
Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation...
Abhishek Mishra, Mugilan Arulvanan, Reshma Ashok +3 more
Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population...
Saeid Jamshidi, Omar Abdul Wahab, Foutse Khomh +1 more
Federated learning (FL) has become an effective paradigm for privacy-preserving, distributed Intrusion Detection Systems (IDS) in cyber-physical and...
Edward Y. Chang, Longling Geng
Inference-time scaling can amplify reasoning pathologies: sycophancy, rung collapse, and premature certainty. We present RAudit, a diagnostic...
Yanghao Su, Wenbo Zhou, Tianwei Zhang +4 more
Emergent Misalignment refers to a failure mode in which fine-tuning large language models (LLMs) on narrowly scoped data induces broadly misaligned...
Charles Westphal, Keivan Navaie, Fernando E. Rosas
Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels. Prior work demonstrated this threat but relied on...
Haoyun Yang, Ronghong Huang, Yong Fang +4 more
Transport Layer Security (TLS) is fundamental to secure online communication, yet vulnerabilities in certificate validation that enable...
Holly Trikilis, Pasindu Marasinghe, Fariza Rashid +1 more
Phishing continues to be one of the most prevalent attack vectors, making accurate classification of phishing URLs essential. Recently, large...
Pragatheeswaran Vipulanandan, Kamal Premaratne, Dilip Sarkar
Large language models (LLMs) exhibit strong generative capabilities but remain vulnerable to confabulations, fluent yet unreliable outputs that vary...
Binyan Xu, Fan Yang, Xilin Dai +2 more
Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal...
Eranga Bandara, Ross Gore, Sachin Shetty +9 more
6G networks are expected to be AI-native, intent-driven, and economically programmable, requiring fundamentally new approaches to network slice...
Xingcheng Xu, Jingjing Qu, Qiaosheng Zhang +4 more
The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral...
Henry Chen, Victor Aranda, Samarth Keshari +2 more
Prompt-based attack techniques are one of the primary challenges in securely deploying and protecting LLM-based AI systems. LLM inputs are an...
Zihan Wu, Jie Xu, Yun Peng +2 more
Large Language Models (LLMs) struggle to automate real-world vulnerability detection due to two key limitations: the heterogeneity of vulnerability...
Mengyuan Jin, Zehui Liao, Yong Xia
Multimodal Large Language Models (MLLMs) have shown remarkable capability in assisting disease diagnosis in medical visual question answering (VQA)....
Jiahe Guo, Xiangran Guo, Yulin Hu +8 more
Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized...
Xianya Fang, Xianying Luo, Yadong Wang +8 more
Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models...
Zhining Liu, Tianyi Wang, Xiao Lin +9 more
Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments...
Saswat Das, Ferdinando Fioretto
This work addresses the computational challenge of enforcing privacy for agentic Large Language Models (LLMs), where privacy is governed by the...
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