AI Threat AlertToolMEDIUM
The Safeguard Worked. Is the LLM System Safer?
Pingyu Wu, Weiming Zhang, Nenghai Yu
Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control...
AI Security Research
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.
- Adversarial attacks
- Model defenses
- Red-teaming benchmarks
- Surveys
- Security tooling
- Total4,319
- Attack1,676
- Benchmark1,229
- Defense610
- Tool432
- Survey252
Showing 761–780 of 1,739 papers
Clear filtersBenchmarkHIGH
Validity-Aware Jailbreak Evaluation for Large Language Models
Qilong Wu, Sahil Wadhwa, Pranab Mohanty +2 more
Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevailing methodologies rely primarily on refusal...
SurveyMEDIUM
EvoFlint: An Evolutionary Atlas of Multi-Turn LLM Vulnerabilities
Feitong Qiao, Liren Peng, Shiming Ren +7 more
Frontier language models that refuse harmful single-turn prompts often comply when the same intent is reached gradually over many turns, making...
AttackMEDIUM
TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning
Muhaimin Bin Munir, Akib Jawad Ononto, Nazia Shehnaz Joynab +2 more
Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implicit trust in retrieved documents creates a critical...
AttackLOW
NeuroPriv: Adversarial Representation Learning for Privacy in Wearable EEG Systems
Sarmistha Sarna Gomasta, Bhawana Chhaglani, Prashant Shenoy
Wearable EEG systems may expose sensitive information beyond their intended health function, creating substantial risks to neuroprivacy. In this...
BenchmarkMEDIUM
Workload Identification with Physical Side Channels for AI Governance
Simone Gargiulo, Gabriel Kulp
AI compute verification is one of the first tangible and tractable points for international policy aimed at AI governance. Determining whether...
ToolMEDIUM
Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems
Panduranga Sai Varma Dantuluri, Jyotirmoy Sundi
Autonomous LLM agents increasingly act on a user's behalf: they hold credentials, call tools and services, and spawn sub-agents that act further on...
OtherLOW
DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening
Yung Wei Shueh, Zhi-Jie Chen, Chia-Hsuan Hsu +9 more
Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and...
AttackMEDIUM
TrainSDC: Characterizing and Mitigating Silent Data Corruption in Large Language Model Training
Zhipeng Xia, Haotian Xu, Siyu Yun +4 more
LLM training is increasingly vulnerable to silent data corruption (SDC), yet existing protection methods largely treat Transformer computations...
DefenseMEDIUM
Do VLMs Share Safety Neurons Across Modalities?
Jiaxuan Li, Jiahao Zhang, Duc Minh Vo +3 more
Vision-language models (VLMs) can comply with harmful requests delivered through images, even when their LLM backbones would refuse the same content...
AttackHIGH
The Fragility of Jailbreak Robustness Across Operational States
Yuna Park, Hwang Youn Kim, Yujin Kim +3 more
Existing jailbreak evaluations typically characterize robustness using a single attack success rate (ASR) measured in a default configuration (the...
BenchmarkLOW
WildSEEK: Evaluating Language Models for Information-Seeking
Tanise Ceron, Joachim Baumann, Elisa Bassignana +3 more
Language models are increasingly mediating information access to end users, urging a systematic evaluation of their responses for a fair and reliable...
AttackHIGH
The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal
Md Mokarram Chowdhury, Ernie Chang, Yang Li
Large language models are trained to follow instructions while refusing harmful requests. Jailbreaks exploit this balance to elicit content a model...
ToolHIGH
ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems
Shiqian Zhao, Yangfan Zhou, Xinfeng Li +5 more
Recently, large language model (LLM) agents, such as Codex, Claude Code, and OpenClaw, have become capable of planning and executing long-horizon...
AttackHIGH
EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
Doyun Kim, Chanwoo Kim, Sugyeong Eo +2 more
LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task...
BenchmarkLOW
Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models
Yangmin Huang, Shu Quan, He Geng +5 more
Medical knowledge changes continually, making large language models vulnerable to relying on outdated yet clinically plausible information. We study...
DefenseMEDIUM
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
Yizhe Zeng, Chenxu Niu, Wei Zhang +7 more
Backdoor attacks pose a serious threat to large language models (LLMs), but existing defenses remain fragmented, failing to pro?vide unified defense...
ToolMEDIUM
Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems
Lifei Liu, Haoran Yu
Multi-agent applications delegate work across independently operated deployers. After an incident, a verifier must answer two questions: which...
ToolHIGH
Will the User Ever Know? Covert Indirect Prompt Injection on Tool-Using LLM Agents
Yunseok Lee, Yunji Kim, Woojin Lee
As LLM agents take real-world actions through tools, indirect prompt injection (IPI) has emerged as a serious threat. The standard metric, Attack...
ToolMEDIUM
Extracting Knowledge from Tools in LLM Agents
Chuanchao Zang, Jianing Wang, Wenyu Chen +6 more
LLM agents commonly use knowledge-based tools and access their underlying files, databases, and search indexes through tool invocation. This...
Frequently asked questions
What is AI security research?
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.
How many AI security papers does AI Threat Alert track?
AI Threat Alert indexes 4,319+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Where do the research papers come from?
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.
What topics does the AI security research cover?
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.
How is this different from a generic paper search?
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.
Track AI security vulnerabilities in real time
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