#ai-vulnerability News & Analysis

6 articles tagged with #ai-vulnerability. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

6 articles

AIBearisharXiv – CS AI · Apr 107/10

🧠

BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack

Researchers have demonstrated the first multi-targeted backdoor attack against graph neural networks (GNNs) in graph classification tasks, using a novel subgraph injection method that simultaneously redirects multiple predictions to different target labels while maintaining clean accuracy. The attack shows high efficacy across multiple GNN architectures and datasets, with resilience against existing defense mechanisms, exposing significant vulnerabilities in GNN security.

AIBearisharXiv – CS AI · Mar 177/10

🧠

DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems

Researchers developed DECEIVE-AFC, an adversarial attack framework that can significantly compromise AI-based fact-checking systems by manipulating claims to disrupt evidence retrieval and reasoning. The attacks reduced fact-checking accuracy from 78.7% to 53.7% in testing, highlighting major vulnerabilities in LLM-based verification systems.

AIBearisharXiv – CS AI · Mar 117/10

🧠

When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models

Researchers have developed UPA-RFAS, a new adversarial attack framework that can successfully fool Vision-Language-Action (VLA) models used in robotics with universal physical patches that transfer across different models and real-world scenarios. The attack exploits vulnerabilities in AI-powered robots by using patches that can hijack attention mechanisms and cause semantic misalignment between visual and text inputs.

AIBearisharXiv – CS AI · Mar 67/10

🧠

Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models

Researchers discovered a new vulnerability in multimodal large language models where specially crafted images can cause significant performance degradation by inducing numerical instability during inference. The attack method was validated on major vision-language models including LLaVa, Idefics3, and SmolVLM, showing substantial performance drops even with minimal image modifications.

AIBearisharXiv – CS AI · Mar 57/10

🧠

Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions

Researchers have developed Image-based Prompt Injection (IPI), a black-box attack that embeds adversarial instructions into natural images to manipulate multimodal AI models. Testing on GPT-4-turbo achieved up to 64% attack success rate, demonstrating a significant security vulnerability in vision-language AI systems.

🧠 GPT-4

AIBearisharXiv – CS AI · Mar 37/106

🧠

Learning to Attack: A Bandit Approach to Adversarial Context Poisoning

Researchers developed AdvBandit, a new black-box adversarial attack method that can exploit neural contextual bandits by poisoning context data without requiring access to internal model parameters. The attack uses bandit theory and inverse reinforcement learning to adaptively learn victim policies and optimize perturbations, achieving higher victim regret than existing methods.