arXiv Machine Learning
Jul 9
The Power of Backdoor Absorption in Community Training
arXiv:2607. 06643v1 Announce Type: cross Abstract: Backdoor attacks severely threaten large-scale AI models.
Self-Creating Random Walks for Decentralized Learning under Pac-Man Attacks
arXiv:2601. 07674v2 Announce Type: replace-cross Abstract: Random walk (RW)-based algorithms have long been popular in distributed systems due to low overheads and scalability, with recent growing applications in decentralized learning.
Related stories
arXiv AI
Jun 12
PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent
arXiv:2606. 12896v1 Announce Type: cross Abstract: While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more attention and exploration.
arXiv Machine Learning
Jul 17
PAC Learning in Turn-Based Stochastic Games with Reachability Objectives: A Decentralized Private Approach via Expected Conditional Distance
arXiv:2607. 14877v1 Announce Type: new Abstract: Reachability is the most fundamental logical objective, yet it is notoriously difficult to learn in reinforcement learning settings: even for Markov decision processes, PAC learning of reachability is impossible without additional assumptions.
arXiv Machine Learning
Jul 7
Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
arXiv:2506. 18020v3 Announce Type: replace Abstract: Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers.
arXiv Machine Learning
Aug 10
Online Security Learning in Cooperative Multi-Agent Systems under Hidden Byzantine Attacks
arXiv:2608. 06520v1 Announce Type: new Abstract: We study online cooperative control of a multi-agent system under Byzantine attacks.
arXiv Machine Learning
Jul 7
Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
arXiv:2506. 07468v4 Announce Type: replace Abstract: Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities.
arXiv Machine Learning
6d ago
Defending against Model Extraction for GNNs with Model Reprogramming
arXiv:2608. 11495v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS).
arXiv Machine Learning
Jun 15
Private Prediction via PAC Privacy
arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.
arXiv Machine Learning
Jul 24
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.
arXiv Machine Learning
Jun 2
IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning
arXiv:2606. 02563v1 Announce Type: new Abstract: Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity.
arXiv Machine Learning
Aug 11
Decision-Focused Learning in Network Interdiction Games
arXiv:2608. 09036v1 Announce Type: cross Abstract: We study decision-focused learning (DFL) in shortest-path network interdiction (SPNI) games, a Stackelberg game where an interdictor (leader) strengthens the networks' arcs against attacks, while an evader (follower) who is uncertain about costs of attacking network arcs relies on a machine-learned predictor to identify the shortest path.
arXiv Machine Learning
Jun 18
Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning
arXiv:2606. 19129v1 Announce Type: cross Abstract: Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem.