The paper investigates a new attack method called output‑prefix attacks on reasoning LLMs, where an attacker prepends a malicious text to the model’s output, thereby conditioning all subsequent tokens on that prefix. The study systematically isolates the scratchpad reasoning channel as a vulnerable vector and compares three attack types—reasoning‑only, output‑prefix‑only, and combined reasoning‑plus‑output‑prefix—across both exposed and hidden reasoning models. Experiments on three 2026‑era frontier models (Gemini 3 Flash Preview, DeepSeek V4 Flash, and Claude Haiku 4.5) show that reasoning alone is largely ineffective, but adding a trivial output prefix can raise attack success rates to as high as 99% for some models, with contextual prefixes outperforming static ones and susceptibility varying by model.
By Luk\'a\v{s} Br\r{u}na, Robert Bridges, Adam Ek
The paper introduces OverThink, a slowdown attack that forces reasoning language models (RLMs) to produce many more reasoning tokens while still giving correct answers. By injecting decoy reasoning problems—such as Markov decision processes, language translation, or graphic comprehension—into the model’s context, attackers can dramatically increase token generation (up to 46× on SQuAD and 17× on coding agents). The study evaluates the attack on both proprietary and open-source RLMs across multiple datasets, explores multimodal and coding‑agent variants, and tests several defenses, concluding that defending against OverThink is challenging and that newer RLMs are even more vulnerable due to higher per‑token costs and increased reasoning token usage.
By Abhinav Kumar, Jaechul Roh, Ali Naseh, Marzena Karpinska, Mohit Iyyer, Amir Houmansadr, Eugene Bagdasarian
arXiv:2606. 07968v1 Announce Type: cross Abstract: Reasoning-capable large language models can be induced to spend their generation budget on injected decoy tasks rather than answering the user's question, causing denial of service when no final answer is produced and denial of wallet when excess output tokens are billed.
By Abid Aziz, Hafsa Binte Kibria
The paper introduces Semantic Overlays, a steering technique that adds non‑textual annotations to a language model’s input by applying learned adapters at specific prefill positions. These overlays create an out‑of‑band channel that encodes span identity and complex semantics, enabling the model to interpret marked text differently—such as rewriting code in a specified language or ignoring executable instructions. Experiments show that Semantic Overlays dramatically reduce prompt‑injection success rates while preserving model utility and readability of marked spans.
By Joshua Penman
arXiv:2506. 07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities.
By Jingyuan Ma, Rui Li, Zheng Li, Junfeng Liu, Heming Xia, Lei Sha, Zhifang Sui
arXiv:2510.17904v3 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them par...
By Amirkia Rafiei Oskooei, Mehmet S. Aktas
arXiv:2606. 05609v1 Announce Type: cross Abstract: As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbreak attacks becomes increasingly critical.
By Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim, Yunseok Lee, Woojin Lee
Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned models (7-31B) and five attack types (GCG, AutoDAN, DeepInception, prefilling, intent laundering).
The paper investigates whether neuro‑symbolic (NeSy) AI models, which combine neural perception with symbolic reasoning, can mitigate backdoor attacks. It presents a systematic evaluation comparing the NeSy framework DeepProbLog to baseline neural networks across eight backdoor settings and four reasoning tasks. Results indicate that NeSy models are generally more robust than pure neural models, but their resilience depends heavily on how strictly the reasoning process is enforced and its alignment with the attack target.
By Marco Antonio Corallo, Andrea Agiollo, Mauro Conti, Alberto Giaretta
arXiv:2503. 24191v4 Announce Type: replace-cross Abstract: Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers.
By Shuoming Zhang, Jiacheng Zhao, Hanyuan Dong, Ruiyuan Xu, Zhicheng Li, Yangyu Zhang, Shuaijiang Li, Yuan Wen, Chunwei Xia, Zheng Wang, Xiaobing Feng, Huimin Cui
arXiv:2609.23587v1 Announce Type: new
Abstract: Large reasoning models (LRMs) incur high inference costs, often mitigated by efficiency techniques like quantization and pruning. However, the impact o...
By Yifei Yang, Zouying Cao, Xingrui Wang, Xiao Zhou, Yuexian Li, Dongjie Yang, Hai Zhao
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.
By Yiting Qu, Ziqing Yang, Chi Cui, Ye Leng, Junjie Chu, Yang Zhang