#poisoning-attacks News & Analysis

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

6 articles

AIBearisharXiv – CS AI · Jun 17/10

🧠

Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation

Researchers demonstrate a novel poisoning attack on retrieval-augmented text-to-music systems where attackers inject malicious captions into music databases to manipulate generation outputs toward attacker-chosen targets while maintaining alignment with original user prompts. The attack reveals a critical integrity vulnerability in AI systems that depend on external knowledge bases for prompt augmentation.

AIBearisharXiv – CS AI · Apr 147/10

🧠

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward

Researchers have discovered a critical vulnerability in Reinforcement Learning with Verifiable Rewards (RLVR), an emerging training paradigm that enhances LLM reasoning abilities. By injecting less than 2% poisoned data into training sets, attackers can implant backdoors that degrade safety performance by 73% when triggered, without modifying the reward verifier itself.

AIBearisharXiv – CS AI · Mar 47/102

🧠

Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs

Researchers discovered a new stealth poisoning attack method targeting medical AI language models during fine-tuning that degrades performance on specific medical topics without detection. The attack injects poisoned rationales into training data, proving more effective than traditional backdoor attacks or catastrophic forgetting methods.

AIBearisharXiv – CS AI · Mar 37/104

🧠

Stealthy Poisoning Attacks Bypass Defenses in Regression Settings

Researchers have developed new stealthy poisoning attacks that can bypass current defenses in regression models used across industrial and scientific applications. The study introduces BayesClean, a novel defense mechanism that better protects against these sophisticated attacks when poisoning attempts are significant.

AINeutralarXiv – CS AI · May 276/10

🧠

Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control

Researchers introduce Cordon-MAS, a new defense framework against poisoning attacks on retrieval-augmented generation (RAG) systems. The framework reduces attack success rates by 92.4% by enforcing information-flow control that prevents synthesis agents from directly accessing untrusted evidence, addressing a critical vulnerability in AI systems used for high-stakes applications.

AINeutralarXiv – CS AI · May 16/10

🧠

AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning

Researchers propose AdaBFL, a Byzantine-robust federated learning method that uses adaptive multi-layer defense mechanisms to protect distributed machine learning systems from poisoning attacks by malicious clients. The approach balances defense against multiple attack types without requiring server-side dataset access, with proven convergence properties on non-IID data.