The paper investigates whether increased computational resources for an attacker can make adversarial attacks transferable across all defenders. It finds that for classification tasks, a quadratic resource gap guarantees either a transferable attack or a defense, whereas for generative tasks this guarantee fails. The authors also show that a defense that adds computation after seeing the input can be provably stronger than any fixed-model defense, suggesting that inference-time compute can enhance robustness.
arXiv:2509. 23689v2 Announce Type: replace Abstract: Model Merging (MM) has proven to be an effective alternative to multi-task learning, where several fine-tuned models are merged, without access to the tasks' training data, into one model that retains performance across different tasks.
HE-Guardrail is a framework that applies homomorphic encryption to enforce guardrails against jailbreak attacks during encrypted large language model inference. It evaluates guardrail mechanisms—Llama Guard, JBShield, and GradSafe—directly on encrypted data, deciding whether to return the model’s response to the client. The approach preserves confidentiality while closely matching the decisions of plaintext guardrails, offering varied security-efficiency-utility trade‑offs.
The paper investigates how adversarial examples transfer between client models in federated learning and explores the relationship between these examples and client data distributions. It proposes a defense strategy based on adversarial training that leverages the transferability of model robustness. Experiments on real-life datasets demonstrate that the new attack and defense methods outperform existing state‑of‑the‑art approaches.
arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.
arXiv:2606. 11409v1 Announce Type: cross Abstract: Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly.
The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of machine learning models. However, the involvement of a...
arXiv:2609.32602v2 Announce Type: replace-cross Abstract: Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacke...
OVIG is an optimistic verification framework that audits AI training by replaying the process and comparing gradient differences against an empirically calibrated boundary. It treats any gradient difference exceeding this boundary as a malicious deviation. By partitioning training into stride‑s intervals and storing evidence only at interval endpoints, OVIG dramatically reduces off‑chain storage and transmission costs while maintaining zero attack success rate across language, vision, and diffusion workloads.
arXiv:2606. 10091v1 Announce Type: cross Abstract: Machine learning (ML) models are susceptible to various security, privacy, and fairness risks.
arXiv:2610.06083v2 Announce Type: replace Abstract: Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This pa...
arXiv:2510. 10982v2 Announce Type: replace-cross Abstract: Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misuse, particularly by enforcing purpose limitation in downstream AI applications.
arXiv:2607. 06643v1 Announce Type: cross Abstract: Backdoor attacks severely threaten large-scale AI models.