#machine-learning-security News & Analysis

29 articles tagged with #machine-learning-security. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

29 articles

AINeutralarXiv – CS AI · May 116/10

🧠

Towards Differentially Private Reinforcement Learning with General Function Approximation

Researchers present the first theoretical framework for differentially private reinforcement learning with general function approximation, achieving regret bounds of Õ(K^3/5) that match linear-case performance. This breakthrough extends privacy guarantees beyond tabular and linear settings, combining batched policy updates with the exponential mechanism for improved privacy-utility tradeoffs in online RL systems.

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.

AIBullisharXiv – CS AI · Apr 146/10

🧠

QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits

Researchers introduce QShield, a hybrid quantum-classical neural network architecture that combines traditional CNNs with quantum processing modules to defend deep learning models against adversarial attacks. Testing on MNIST, OrganAMNIST, and CIFAR-10 datasets shows the hybrid approach maintains accuracy while substantially reducing attack success rates and increasing computational costs for adversaries.

AINeutralarXiv – CS AI · Apr 136/10

🧠

CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion

Researchers introduce CLIP-Inspector, a backdoor detection method for prompt-tuned CLIP models that reconstructs hidden triggers using out-of-distribution images to identify if a model has been maliciously compromised. The technique achieves 94% detection accuracy and enables post-hoc model repair, addressing critical security vulnerabilities in outsourced machine learning services.

← PrevPage 2 of 2