#backdoor-attack News & Analysis

3 articles tagged with #backdoor-attack. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBearisharXiv – CS AI · Jun 97/10

🧠

Targeting World Models to Compromise Robot Learning Pipelines

Researchers demonstrate a novel data poisoning attack targeting world models used in robot learning pipelines, showing how malicious prompts or dynamics hidden in training data can be activated only when processed through world models to generate unsafe robotic policies. The attack bypasses traditional safety measures by appearing benign in ground truth datasets while compromising downstream robot learning systems, affecting both action-conditioned and text-conditioned models.

AIBearisharXiv – CS AI · May 17/10

🧠

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors

Researchers demonstrate a novel attack that steals sensitive secrets (API keys, personal identifiers, financial records) from locally fine-tuned language models by embedding malicious code in model architectures. The attack achieves over 98% success rate and bypasses current defense mechanisms including differential privacy and code auditing, exposing a critical supply-chain vulnerability in AI model development.

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.