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 21–40 of 264 papers
Clear filtersVirginia Ceccatelli, Yejin Jeon, David Ifeoluwa Adelani
Large audio language models (LALMs) are increasingly deployed in real-world applications, yet their safety alignment is still primarily evaluated on...
Minseok Choi, Seungbin Yang, Dongjin Kim +5 more
Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety...
Zhibo Zhang, Yuxi Li, Zhen Ouyang +2 more
Mixture-of-Experts (MoE) LLMs rely on sparse, router-driven expert activation, yet how safety alignment interacts with routed expert specialization...
Chao Ding, Mouxiao Bian, Tianbin Li +12 more
Large language models(LLMs) increasingly match expert performance on licensing examinations, yet routine clinical use remains limited because...
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...
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...
Andy Han, Kristina Fujimoto, Avidan Shah +5 more
Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings....
Scott Freitas, Amir Gharib
Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft...
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...
Isaac David, Arthur Gervais
Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents?...
Jiahe Guo, Xiangran Guo, Jiaxuan Chen +6 more
Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text...
Md Navid Bin Islam, Sajal Saha, Senior Member
Machine-learning-based Intrusion Detection Systems (IDS) have achieved impressive accuracy in classifying network attacks, yet they consistently fall...
Ahmad Al-Tawaha, Shangding Gu, Peizhi Niu +2 more
Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often...
Pratinav Seth, Vinay Kumar Sankarapu
This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI...
Itay Zloczower, Eyal Lenga, Gilad Gressel +1 more
Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are...
Kebin Contreras, Carlos Hinojosa, Jorge Bacca +1 more
Computer-use agents are increasingly capable of operating on real operating systems, but this capability has also increased the risks posed by prompt...
Shravan Doda
Final-token safety probes monitor a single hidden state after prompt prefill, but jailbreak prompts can contain probe-visible unsafe evidence...
Sina Mavali, David Pape, Jonathan Evertz +5 more
Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must...
Xinyi Zeng, Xue Yang, Jingyuan Zhang +5 more
Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant...
John T. Halloran
Large language model (LLM) alignment algorithms typically consist of post-training over preference pairs. While such algorithms are widely used to...
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