arXiv:2607. 28959v1 Announce Type: cross Abstract: Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especially for large language models (LLMs).
arXiv:2510. 02999v5 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses.
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.
arXiv:2606. 07970v1 Announce Type: cross Abstract: Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which could compromise the safety alignment of LLMs with only a few steps of supervised finetuning (SFT) on poisoned datasets.
arXiv:2607. 08883v1 Announce Type: new Abstract: Behavioral alignment in large language models often masks fragile internal safety representations.
arXiv:2606. 07696v1 Announce Type: cross Abstract: Activation steering has become a popular training-free method to control LLM behavior by injecting precomputed direction vectors into the model's residual stream at inference time.
arXiv:2606. 15441v1 Announce Type: cross Abstract: Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution.
The paper introduces FAB, an attack that uses meta‑learning to embed dormant adversarial behaviors into large language models (LLMs). These behaviors remain inactive until the model is finetuned by downstream users, at which point the model can exhibit unwanted actions such as unsolicited advertising, jailbreakability, or over‑refusal. FAB is shown to be effective across multiple LLMs and resilient to various finetuning settings.
Gradient Mirage is a defense for large language model split learning that disrupts the assumption that exposed gradients faithfully reflect the client’s full-label training objective, thereby thwarting gradient matching attacks. It introduces inconsistencies across objective, direction, and scale by using selective autoregressive supervision, scale blinding, and directional privatization with a von Mises-Fisher mechanism. The method preserves utility through dual-track backpropagation and bottom-gradient recovery, achieving a stronger privacy‑utility trade‑off in experiments.
arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.
Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense.
arXiv:2605. 12813v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs.
arXiv:2606. 00738v1 Announce Type: cross Abstract: Adversarial Training (AT) is a leading defense against adversarial examples but often suffers from Catastrophic Overfitting (CO) in efficient single-step variants, where robustness to multi-step attacks collapses despite high single-step performance.