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
2,560+ academic papers on AI security, attacks, and defenses
Total
2,560
Attack
982
Benchmark
736
Defense
350
Tool
275
Survey
144
Showing 361–380 of 635 papers
Clear filters 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 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...
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...
Attack HIGH
EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion
Zhen Liang, Hai Huang, Zhengkui Chen
Large language models (LLMs), such as ChatGPT, have achieved remarkable success across a wide range of fields. However, their trustworthiness remains...
Attack HIGH
Adaptive Trust Consensus for Blockchain IoT: Comparing RL, DRL, and MARL Against Naive, Collusive, Adaptive, Byzantine, and Sleeper Attacks
Soham Padia, Dhananjay Vaidya, Ramchandra Mangrulkar
Securing blockchain-enabled IoT networks against sophisticated adversarial attacks remains a critical challenge. This paper presents a trust-based...
Attack HIGH
Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models
Zongmin Zhang, Zhen Sun, Yifan Liao +5 more
Prompt-driven Video Segmentation Foundation Models (VSFMs) such as SAM2 are increasingly deployed in applications like autonomous driving and digital...
Attack HIGH
Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models
Mengqi He, Xinyu Tian, Xin Shen +4 more
Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, a measure of model uncertainty,...
Attack HIGH
Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study
Duo Chai, Zizhen Liu, Shuhuai Wang +4 more
Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time,...
Attack HIGH
LLM-Driven Feature-Level Adversarial Attacks on Android Malware Detectors
Tianwei Lan, Farid Naït-Abdesselam
The rapid growth in both the scale and complexity of Android malware has driven the widespread adoption of machine learning (ML) techniques for...
Attack HIGH
Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
Xinjie Xu, Shuyu Cheng, Dongwei Xu +2 more
In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major...
Attack HIGH
GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs
Lichao Wu, Sasha Behrouzi, Mohamadreza Rostami +2 more
Mixture-of-Experts (MoE) architectures have advanced the scaling of Large Language Models (LLMs) by activating only a sparse subset of parameters per...
Attack HIGH
AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs
Yihan Wang, Huanqi Yang, Shantanu Pal +1 more
The integration of Large Language Models (LLMs) into wearable sensing is creating a new class of mobile applications capable of nuanced human...
Attack HIGH
Real-World Adversarial Attacks on RF-Based Drone Detectors
Omer Gazit, Yael Itzhakev, Yuval Elovici +1 more
Radio frequency (RF) based systems are increasingly used to detect drones by analyzing their RF signal patterns, converting them into spectrogram...
Attack HIGH
Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models
Linzhi Chen, Yang Sun, Hongru Wei +1 more
Low-Rank Adaptation (LoRA) has emerged as an efficient method for fine-tuning large language models (LLMs) and is widely adopted within the...
Attack HIGH
GShield: Mitigating Poisoning Attacks in Federated Learning
Sameera K. M., Serena Nicolazzo, Antonino Nocera +2 more
Federated Learning (FL) has recently emerged as a revolutionary approach to collaborative training Machine Learning models. In particular, it enables...
Attack HIGH
PromptScreen: Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline
Akshaj Prashanth Rao, Advait Singh, Saumya Kumaar Saksena +1 more
Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen,...
Attack HIGH
MEEA: Mere Exposure Effect-Driven Confrontational Optimization for LLM Jailbreaking
Jianyi Zhang, Shizhao Liu, Ziyin Zhou +1 more
The rapid advancement of large language models (LLMs) has intensified concerns about the robustness of their safety alignment. While existing...
Attack HIGH
Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors
Huixin Zhan
Genomic Foundation Models (GFMs), such as Evolutionary Scale Modeling (ESM), have demonstrated remarkable success in variant effect prediction....
Attack HIGH
Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
Kai Hu, Abhinav Aggarwal, Mehran Khodabandeh +6 more
This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model (LLM) safety evaluation from a...
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