AI Threat AlertAttackLOW
Incentive-Aligned Multi-Source LLM Summaries
Yanchen Jiang, Zhe Feng, Aranyak Mehta
Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a...
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 1641–1660 of 1,676 papers
Clear filtersAttackHIGH
SecInfer: Preventing Prompt Injection via Inference-time Scaling
Yupei Liu, Yanting Wang, Yuqi Jia +2 more
Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses...
AttackMEDIUM
PRIVMARK: Private Large Language Models Watermarking with MPC
Thomas Fargues, Ye Dong, Tianwei Zhang +1 more
The rapid growth of Large Language Models (LLMs) has highlighted the pressing need for reliable mechanisms to verify content ownership and ensure...
AttackHIGH
TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models
Zhifang Zhang, Qiqi Tao, Jiaqi Lv +3 more
Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable...
AttackMEDIUM
FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems
Yuzhen Long, Songze Li
Autonomous driving systems increasingly rely on multi-agent architectures powered by large language models (LLMs), where specialized agents...
AttackMEDIUM
Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in Large Language Models
Jongwook Han, Jongwon Lim, Injin Kong +1 more
Large language models can express values in two main ways: (1) intrinsic expression, reflecting the model's inherent values learned during training,...
AttackMEDIUM
AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
Zihao Zhu, Xinyu Wu, Gehan Hu +3 more
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex problem-solving through Chain-of-Thought (CoT) reasoning. However,...
AttackHIGH
StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
Yixu Wang, Yan Teng, Yingchun Wang +1 more
Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have transformed vision model adaptation, enabling the rapid deployment of customized...
AttackHIGH
Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
Zhaoqi Wang, Daqing He, Zijian Zhang +4 more
Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt...
AttackMEDIUM
Dual-Space Smoothness for Robust and Balanced LLM Unlearning
Han Yan, Zheyuan Liu, Meng Jiang
With the rapid advancement of large language models, Machine Unlearning has emerged to address growing concerns around user privacy, copyright...
AttackHIGH
Preventing Robotic Jailbreaking via Multimodal Domain Adaptation
Francesco Marchiori, Rohan Sinha, Christopher Agia +4 more
Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly deployed in robotic environments but remain vulnerable to...
AttackHIGH
Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
Zi Liang, Qingqing Ye, Xuan Liu +3 more
Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large...
AttackHIGH
GuardNet: Graph-Attention Filtering for Jailbreak Defense in Large Language Models
Javad Forough, Mohammad Maheri, Hamed Haddadi
Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and...
AttackMEDIUM
LLM Watermark Evasion via Bias Inversion
Jeongyeon Hwang, Sangdon Park, Jungseul Ok
Watermarking offers a promising solution for detecting LLM-generated content, yet its robustness under realistic query-free (black-box) evasion...
AttackHIGH
AntiFLipper: A Secure and Efficient Defense Against Label-Flipping Attacks in Federated Learning
Aashnan Rahman, Abid Hasan, Sherajul Arifin +5 more
Federated learning (FL) enables privacy-preserving model training by keeping data decentralized. However, it remains vulnerable to label-flipping...
AttackHIGH
Boundary on the Table: Efficient Black-Box Decision-Based Attacks for Structured Data
Roie Kazoom, Yuval Ratzabi, Etamar Rothstein +1 more
Adversarial robustness in structured data remains an underexplored frontier compared to vision and language domains. In this work, we introduce a...
AttackHIGH
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Hwan Chang, Yonghyun Jun, Hwanhee Lee
The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for...
AttackMEDIUM
What Do They Fix? LLM-Aided Categorization of Security Patches for Critical Memory Bugs
Xingyu Li, Juefei Pu, Yifan Wu +13 more
Open-source software projects are foundational to modern software ecosystems, with the Linux kernel standing out as a critical exemplar due to its...
AttackHIGH
Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
Wonjun Lee, Haon Park, Doehyeon Lee +2 more
Along with the rapid advancement of numerous Text-to-Video (T2V) models, growing concerns have emerged regarding their safety risks. While recent...
AttackMEDIUM
Adversarial training with restricted data manipulation
David Benfield, Stefano Coniglio, Phan Tu Vuong +1 more
Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as...
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