arXiv AI September 11, 2026 By Thomas Rivasseau

Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning

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.

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 AI

Sep 21

HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference

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.

By Byeongseo Min, Yongwoo Lee, Young-Sik Kim, Yongjune Kim

llms safety

arXiv Machine Learning

Jun 4

Bypassing Prompt Guards in Production with Controlled-Release Prompting

arXiv:2510. 01529v3 Announce Type: replace Abstract: Ball et al.

By Jaiden Fairoze, Sanjam Garg, Keewoo Lee, Mingyuan Wang

llms safety

arXiv AI

Jul 7

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs

arXiv:2508. 10031v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks.

By Jinhwa Kim, Ian G. Harris

llms fine-tuning benchmarks safety

arXiv AI

Sep 10

SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement

arXiv:2609.05850v1 Announce Type: cross Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has reve...

By Quoc Viet Vo, Trung Le, Damith C. Ranasinghe, Ehsan Abbasnejad

llms benchmarks safety

arXiv Computation and Language

Sep 23

Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs

arXiv:2609.26185v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive capabilities across many applications but remain vulnerable to jailbreak attacks, which elicit ha...

By Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo, Kaichen Yang

llms rag fine-tuning safety

arXiv AI

Jun 11

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

arXiv:2606. 11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code.

By Yitong Zhang, Shiteng Lu, Jia Li

llms benchmarks safety

One email a morning, machine-written

Related stories

HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference

Bypassing Prompt Guards in Production with Controlled-Release Prompting

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs

SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement

Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code