arXiv:2610.19968v1 Announce Type: new Abstract: Federated fine-tuning enables large language models (LLMs) to learn collaboratively from distributed client data, but malicious client updates can comp...
arXiv:2511. 11439v3 Announce Type: replace-cross Abstract: Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics.
arXiv:2606. 29841v1 Announce Type: new Abstract: Continual learning (CL), where a model is trained on a sequence of data tasks, is increasingly being adopted across key fields such as large language models and image recognition, yet it remains highly vulnerable to data poisoning that triggers learning divergence or severe excess risk.
The paper addresses the challenge of adapting malware detection systems to new threats without retraining from scratch, focusing on the Few-Shot Class-Incremental Learning (FSCIL) setting. It proposes a hybrid framework that uses a self-supervised learning backbone pre-trained on malware packets, incorporates Low-Rank Adaptation (LoRA) to adapt the model while preserving core representations, and employs a prototype-based classification head for incremental sessions. Experiments on multiple datasets show that this approach consistently outperforms existing FSCIL baselines and achieves state-of-the-art performance.
arXiv:2507. 18313v2 Announce Type: replace Abstract: Malware evolves rapidly, forcing machine learning-based detectors to be continuously updated.
arXiv:2606. 14078v1 Announce Type: cross Abstract: Existing studies reveal that current backdoor defenses exhibit limited robustness and often fail against specific types of attacks.
Continual learning (CL), where a model is trained on a sequence of data tasks, is increasingly being adopted across key fields such as large language models and image recognition, yet it remains highly vulnerable to data poisoning that triggers learning divergence or severe excess risk. Despite these threats, a principled theoretical foundation in CL for understanding attack and defense remains lacking.
The paper introduces Fed-ADR, a coordinated attack framework where a malicious orchestrator server directs heterogeneous adversarial clients to adapt their gradient updates in real time, thereby evading existing federated learning defenses and drastically reducing global model accuracy. It also presents a lightweight detection mechanism that estimates true client gradients from historical data to spot coordinated attacks, and an in-situ recovery method that restores model performance without restarting training. Experiments on MNIST, Fashion‑MNIST, and CIFAR‑10 show the attack can drop accuracy from over 90% to below 10%, while the defense can recover accuracy to above 90% within a few rounds at a computational cost at least 20× lower than retraining from scratch.
arXiv:2610. 34934v1 Announce Type: new Abstract: Machine learning systems trained on untrusted data are vulnerable to data and backdoor poisoning attacks, in which an adversary corrupts training and test samples to manipulate predictions at inference time.
arXiv:2608. 00732v1 Announce Type: new Abstract: Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject malicious behaviors through data poisoning.
arXiv:2607. 05748v1 Announce Type: new Abstract: The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning.
The paper presents a fast machine unlearning method that uses Hessian analysis to identify correlated training data and applies a closed‑form update rule. This approach achieves an 82× speedup over traditional influence‑function unlearning while maintaining or slightly improving model accuracy. Experiments on seven dataset‑architecture pairs, including CIFAR‑100 with ResNet‑50, show strong forgetting performance and low vulnerability to membership inference attacks.