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 201–220 of 407 papers
Clear filtersOliver Daniels, Perusha Moodley, Benjamin M. Marlin +1 more
Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing...
Yu Fu, Haz Sameen Shahgir, Huanli Gong +3 more
Large language models (LLMs) increasingly combine long-context processing with advanced reasoning, enabling them to retrieve and synthesize...
Yukun Jiang, Hai Huang, Mingjie Li +3 more
By introducing routers to selectively activate experts in Transformer layers, the mixture-of-experts (MoE) architecture significantly reduces...
Shayan Ali Hassan, Tao Ni, Zafar Ayyub Qazi +1 more
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and generation. However, these...
Gautam Siddharth Kashyap, Mark Dras, Usman Naseem
Large Language Models (LLMs) need to be in accordance with human values-being helpful, harmless, and honest (HHH)-is important for safe deployment....
Yunbei Zhang, Kai Mei, Ming Liu +5 more
We present the first large-scale empirical study of Moltbook, an AI-only social platform where 27,269 agents produced 137,485 posts and 345,580...
Chen Chen, Yuchen Sun, Jiaxin Gao +4 more
Large language models (LLMs) are increasingly deployed in security-sensitive applications, yet remain vulnerable to backdoor attacks. However,...
Hema Karnam Surendrababu, Nithin Nagaraj
Machine Learning (ML) models, including Large Language Models (LLMs), are characterized by a range of system-level attributes such as security and...
Daniel Fein, Max Lamparth, Violet Xiang +2 more
Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is...
Rohan Subramanian Thomas, Shikhar Shiromani, Abdullah Chaudhry +4 more
Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain...
Zhenxiong Yu, Zhi Yang, Zhiheng Jin +19 more
As large language models (LLMs) evolve into autonomous agents, their real-world applicability has expanded significantly, accompanied by new security...
Jiacheng Liang, Yuhui Wang, Tanqiu Jiang +1 more
Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable...
Guang Yang, Xing Hu, Xiang Chen +1 more
Large language models (LLMs) for Verilog code generation are increasingly adopted in hardware design, yet remain vulnerable to backdoor attacks where...
Sidahmed Benabderrahmane, Petko Valtchev, James Cheney +1 more
Detecting rare and diverse anomalies in highly imbalanced datasets-such as Advanced Persistent Threats (APTs) in cybersecurity-remains a fundamental...
Rohan Saxena
Fine-tuning language models on narrowly harmful data causes emergent misalignment (EM) -- behavioral failures extending far beyond training...
Zeming Wei, Zhixin Zhang, Chengcan Wu +3 more
Recent advancements in LLMs have led to significant breakthroughs in various AI applications. However, their sophisticated capabilities also...
Ali Mahdavi, Santa Aghapour, Azadeh Zamanifar +1 more
Existing Byzantine robust aggregation mechanisms typically rely on fulldimensional gradi ent comparisons or pairwise distance computations, resulting...
Siqi Wen, Shu Yang, Shaopeng Fu +3 more
Vision Language Action (VLA) models close the perception action loop by translating multimodal instructions into executable behaviors, but this very...
Siqi Wen, Shu Yang, Shaopeng Fu +3 more
Vision Language Action (VLA) models close the perception action loop by translating multimodal instructions into executable behaviors, but this very...
Cláudio Lúcio do Val Lopes, João Marcus Pitta, Fabiano Belém +2 more
The integration of Artificial Intelligence (AI) into clinical settings presents a software engineering challenge, demanding a shift from isolated...
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