AI Threat Alert indexes 4,319+ 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 101–120 of 685 papers
Clear filtersJieyu Li, Jingya Li, Sheng Li +2 more
Agent harnesses, the prompt and tool code around a base model, leak. Claude Code's 512,000 lines were mirrored within hours of a packaging error. A...
Gosha Kozhevnikov, Tyler Tracy
We present Screwtape, a pipeline that converts real agent transcripts into attacks that evade action-only monitors. An LLM attacker edits a...
Qianlong Lan, Anuj Kaul, Vinothini Pandurangan +1 more
Prompt-injection defenses are commonly evaluated as binary detectors, although deployed LLM applications must make operational decisions about...
Joas Antonio dos Santos Barbosa
LLM coding agents such as Claude Code and OpenAI Codex can drive penetration-testing tools, but they reason about an engagement as a flat list of...
Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat +7 more
Large language models are increasingly deployed as autonomous agents for automated program repair, patching software vulnerabilities through...
Yixin Tan, Chia-Yi Hsu, Jiayang Liu +2 more
Automated jailbreak attacks rely on evaluation feedback to optimize adversarial prompts, but existing methods often lack fine-grained diagnostic...
Florian Spelter, Johannes F. Loevenich, Tobias Hürten +4 more
Although Artificial Intelligence (AI)-based Intrusion Detection Systems (IDSs) are increasingly deployed in operational networks, their dependence on...
Adel Khorramrouz, Yi-Chia Wang, Sharon Levy
Social psychology has long described how people can be persuaded to interpret a harmful act as moral. Recent research suggests that Large Language...
Wei-Liang Liu, Cheng-Yen Tsai
Model signing authenticates the full-precision weights W an LLM is released with, yet users run a quantized artifact Q whose producing transformation...
Sarthak Gupta, Priyanka Tembey
Several recent studies propose detecting prompt injections from a language model's internal state. However, these methods do not measure a single...
Chenxu Wang, Xiaoyu Wen, Han Qi +4 more
Large language model (LLM) agents accomplish complex tasks through multi-turn interactions with external tools. However, malicious content embedded...
Kshitij Mishra, Salem Lahlou, Nils Lukas
Indirect prompt injection uses untrusted retrieved content, tool outputs, or agent messages to override an LLM's intended behavior. We show that...
Chengtao Jian, Kai Yang
Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), yet the security of multimodal...
Dominik Seip, Bartol Markovinović, Matthias Hein
The safety of LLM-based agents currently rests on alignment training and safety classifiers, neither of which can rule out that a sophisticated...
Xi Chen, Chunyi Zhou, Rui Zeng +3 more
Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering...
Kaan Kale, Sriram Vishwanath
Linear probes on a model's hidden states are used as cheap monitors for indirect prompt injection: they screen the tool outputs an agent reads and...
Paweł Batorski, Przemysław Spurek, Paul Swoboda
Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin. We show...
Yan-Lun Chen, Pin-Yu Chen, Chia-Mu Yu
Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such...
Qikun Cai, Tao Huang, Chen Hou
LLM agents now act as delegated communication intermediaries: they read private context, draft messages, and send externally visible emails on behalf...
Juann Kim, Minku Kang
Persona vectors are linear directions in the residual-stream activations of LLMs that encode behavioral traits and enable fine-grained control over...
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 4,319+ 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