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.
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.
arXiv:2608. 07274v1 Announce Type: cross Abstract: Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead.
The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning. In light of the observation that a model learns poisonous samples responsible for the backdoor easier than benign samples, these approaches either use a fixed threshold of the training loss for splitting or iteratively learn a reference model as an oracle for identifying benign samples.
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.