arXiv:2608. 09867v1 Announce Type: cross Abstract: Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2607. 00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs).
arXiv:2510. 01529v3 Announce Type: replace Abstract: Ball et al.
arXiv:2609.14003v1 Announce Type: cross Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provid...
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.
arXiv:2608. 20055v1 Announce Type: cross Abstract: Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets.
The paper reports that large language models can acquire cipher-based covert communication skills without fine‑tuning, using prompting or in‑context learning instead. This enables new jailbreak attacks that bypass alignment safeguards by encrypting harmful requests, making them appear as nonsensical text to harmfulness classifiers. The authors demonstrate successful attacks against frontier models from Anthropic, Google, and OpenAI.