AI Threat Alert
Attack HIGH
GCG Attack On A Diffusion LLM
Ruben Neyroud, Sam Corley
While most LLMs are autoregressive, diffusion-based LLMs have recently emerged as an alternative method for generation. Greedy Coordinate Gradient...
AI Security Research
2,104+ academic papers on AI security, attacks, and defenses
Total
2,104
Attack
820
Benchmark
609
Defense
276
Tool
229
Survey
116
Showing 1041–1060 of 2,104 papers
Attack LOW
Privacy-Preserving Semantic Communications via Multi-Task Learning and Adversarial Perturbations
Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1 more
Semantic communications conveys task-relevant meaning rather than focusing solely on message reconstruction, improving bandwidth efficiency and...
Benchmark HIGH
Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service
Jingyu Zhang
Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction...
Benchmark MEDIUM
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
Zhe Huang, Hao Wen, Aiming Hao +6 more
Multimodal Large Language Models (MLLMs) have made remarkable progress in video understanding. However, they suffer from a critical vulnerability: an...
Attack MEDIUM
RAGPart & RAGMask: Retrieval-Stage Defenses Against Corpus Poisoning in Retrieval-Augmented Generation
Pankayaraj Pathmanathan, Michael-Andrei Panaitescu-Liess, Cho-Yu Jason Chiang +1 more
Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm to enhance large language models (LLMs) with external knowledge, reducing...
Survey MEDIUM
The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models
Giuseppe Canale, Kashyap Thimmaraju
Large Language Models (LLMs) are rapidly transitioning from conversational assistants to autonomous agents embedded in critical organizational...
Attack HIGH
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
Yuan Xin, Dingfan Chen, Linyi Yang +2 more
As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model...
Attack MEDIUM
RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress
Ruixuan Huang, Qingyue Wang, Hantao Huang +4 more
Mixture-of-Experts architectures have become the standard for scaling large language models due to their superior parameter efficiency. To...
Survey LOW
Coding With AI: From a Reflection on Industrial Practices to Future Computer Science and Software Engineering Education
Hung-Fu Chang, MohammadShokrolah Shirazi, Lizhou Cao +1 more
Recent advances in large language models (LLMs) have introduced new paradigms in software development, including vibe coding, AI-assisted coding, and...
Attack HIGH
Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack
Roee Ziv, Raz Lapid, Moshe Sipper
Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security...
Defense MEDIUM
Zero-Trust Agentic Federated Learning for Secure IIoT Defense Systems
Samaresh Kumar Singh, Joyjit Roy, Martin So
Recent attacks on critical infrastructure, including the 2021 Oldsmar water treatment breach and 2023 Danish energy sector compromises, highlight...
Survey HIGH
Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing
Panagiotis Theocharopoulos, Ajinkya Kulkarni, Mathew Magimai. -Doss
Large language models (LLMs) are increasingly considered for use in high-impact workflows, including academic peer review. However, LLMs are...
Benchmark MEDIUM
Enhanced Web Payload Classification Using WAMM: An AI-Based Framework for Dataset Refinement and Model Evaluation
Heba Osama, Omar Elebiary, Youssef Qassim +4 more
Web applications increasingly face evasive and polymorphic attack payloads, yet traditional web application firewalls (WAFs) based on static rule...
Tool HIGH
Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks
Toqeer Ali Syed, Mishal Ateeq Almutairi, Mahmoud Abdel Moaty
Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models...
Other LOW
Single LLM Debate, MoLaCE: Mixture of Latent Concept Experts Against Confirmation Bias
Hazel Kim, Philip Torr
Large language models (LLMs) are highly vulnerable to input confirmation bias. When a prompt implies a preferred answer, models often reinforce that...
Defense LOW
Why AI Safety Requires Uncertainty, Incomplete Preferences, and Non-Archimedean Utilities
Alessio Benavoli, Alessandro Facchini, Marco Zaffalon
How can we ensure that AI systems are aligned with human values and remain safe? We can study this problem through the frameworks of the AI...
Defense HIGH
Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation
Toqeer Ali Syed, Mohammad Riyaz Belgaum, Salman Jan +2 more
The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build...
Benchmark HIGH
Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark
Manu, Yi Guo, Kanchana Thilakarathna +5 more
Large Language Models (LLMs) can be driven into over-generation, emitting thousands of tokens before producing an end-of-sequence (EOS) token. This...
Attack HIGH
RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Masking
Jiawei Liu, Zhuo Chen, Rui Zhu +4 more
Neural ranking models have achieved remarkable progress and are now widely deployed in real-world applications such as Retrieval-Augmented Generation...
Defense LOW
ViLaCD-R1: A Vision-Language Framework for Semantic Change Detection in Remote Sensing
Xingwei Ma, Shiyang Feng, Bo Zhang +1 more
Remote sensing change detection (RSCD), a complex multi-image inference task, traditionally uses pixel-based operators or encoder-decoder networks...
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