AI Threat Alert
Attack MEDIUM
LoRA as Oracle
Marco Arazzi, Antonino Nocera
Backdoored and privacy-leaking deep neural networks pose a serious threat to the deployment of machine learning systems in security-critical...
AI Security Research
AI Threat Alert indexes 3,397+ 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
- Total3,397
- Attack1,314
- Benchmark975
- Defense477
- Tool341
- Survey196
Showing 301–320 of 458 papers
Clear filters Attack MEDIUM
The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
Christina Lu, Jack Gallagher, Jonathan Michala +2 more
Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We...
Attack MEDIUM
The Straight and Narrow: Do LLMs Possess an Internal Moral Path?
Luoming Hu, Jingjie Zeng, Liang Yang +1 more
Enhancing the moral alignment of Large Language Models (LLMs) is a critical challenge in AI safety. Current alignment techniques often act as...
Attack MEDIUM
UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning
Feng Zhang, Shijia Li, Chunmao Zhang +7 more
User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and...
Attack MEDIUM
SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
Renyang Liu, Kangjie Chen, Han Qiu +4 more
Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from...
Attack MEDIUM
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation
Abdelaziz Bounhar, Rania Hossam Elmohamady Elbadry, Hadi Abdine +3 more
Steering Large Language Models (LLMs) through activation interventions has emerged as a lightweight alternative to fine-tuning for alignment and...
Attack MEDIUM
MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
Ruiqi Li, Zhiqiang Wang, Yunhao Yao +1 more
To standardize interactions between LLM-based agents and their environments, the Model Context Protocol (MCP) was proposed and has since been widely...
Attack MEDIUM
On the Adversarial Robustness of 3D Large Vision-Language Models
Chao Liu, Ngai-Man Cheung
3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks....
Attack MEDIUM
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
Zenghao Duan, Zhiyi Yin, Zhichao Shi +8 more
Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment....
Attack MEDIUM
Effects of personality steering on cooperative behavior in Large Language Model agents
Mizuki Sakai, Mizuki Yokoyama, Wakaba Tateishi +1 more
Large language models (LLMs) are increasingly used as autonomous agents in strategic and social interactions. Although recent studies suggest that...
Attack MEDIUM
Deep Dive into the Abuse of DL APIs To Create Malicious AI Models and How to Detect Them
Mohamed Nabeel, Oleksii Starov
According to Gartner, more than 70% of organizations will have integrated AI models into their workflows by the end of 2025. In order to reduce cost...
Attack MEDIUM
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
San Kim, Gary Geunbae Lee
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad...
Attack MEDIUM
Enhancing Moral Diagnosis and Correction in Large Language Models
Bocheng Chen, Xi Chen, Han Zi +5 more
Identifying specific moral errors in an input and generating appropriate corrections require moral sensitivity in large language models (LLMs), which...
Attack MEDIUM
Extracting books from production language models
Ahmed Ahmed, A. Feder Cooper, Sanmi Koyejo +1 more
Many unresolved legal questions over LLMs and copyright center on memorization: whether specific training data have been encoded in the model's...
Attack MEDIUM
SWaRL: Safeguard Code Watermarking via Reinforcement Learning
Neusha Javidnia, Ruisi Zhang, Ashish Kundu +1 more
We present SWaRL, a robust and fidelity-preserving watermarking framework designed to protect the intellectual property of code LLM owners by...
Attack MEDIUM
Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization
Jiwei Guan, Haibo Jin, Haohan Wang
Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these...
Attack MEDIUM
Aggressive Compression Enables LLM Weight Theft
Davis Brown, Juan-Pablo Rivera, Dan Hendrycks +1 more
As frontier AIs become more powerful and costly to develop, adversaries have increasing incentives to steal model weights by mounting exfiltration...
Attack MEDIUM
IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection
Jiajie Zhu, Xia Du, Xiaoyuan Liu +4 more
The rapid advancements in artificial intelligence have significantly accelerated the adoption of speech recognition technology, leading to its...
Attack MEDIUM
PatchBlock: A Lightweight Defense Against Adversarial Patches for Embedded EdgeAI Devices
Nandish Chattopadhyay, Abdul Basit, Amira Guesmi +3 more
Adversarial attacks pose a significant challenge to the reliable deployment of machine learning models in EdgeAI applications, such as autonomous...
Attack MEDIUM
Rectifying Adversarial Examples Using Their Vulnerabilities
Fumiya Morimoto, Ryuto Morita, Satoshi Ono
Deep neural network-based classifiers are prone to errors when processing adversarial examples (AEs). AEs are minimally perturbed input data...
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 3,397+ 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