Reflex-Guard is a lightweight, locally‑run guardrail for large language models that uses jailbreak‑aware preprocessing, compact sentence‑transformer embeddings, and seven fast binary classifiers to filter unsafe prompts. It achieves 95.9 % recall on harmful prompts with an end‑to‑end latency of 37.6 ms, outperforming existing solutions such as Llama Guard 2 (255 ms) and SafeDecoding (723 ms). The system can detect all GCG suffix attacks and Base64‑encoded prompts at the default threshold, while DrAttack structured prompts require a lower threshold of 0.03 for optimal detection, and it attains a Reflex Efficiency Score of up to 16.79.
By Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon, Abu-fuad Ahmad, Thi Hong Tran
arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.
By Fangzhou Chen, Shiji Zhao, Mengyang Wang, Qihui Zhu, Ranjie Duan, Maoxun Yuan, Xingxing Wei
Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.
Reflex-Guard is a lightweight, locally running guardrail for large language models that uses jailbreak-aware preprocessing, compact sentence‑transformer embeddings, and seven fast binary classifiers to filter unsafe prompts. It achieves 95.9% recall on harmful prompts with an end‑to‑end latency of 37.6 ms, far faster than existing solutions such as Llama Guard 2 (255 ms) and SafeDecoding (723 ms). The system can detect all GCG suffix attacks and Base64‑encoded prompts at the default threshold, and it attains a Reflex Efficiency Score up to 16.79, outperforming its competitors.
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
By Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang
arXiv:2606. 02640v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to iteratively refine prompts toward harmful goals.
By Huanli Gong, Zhipeng Wei, Yu Fu, Haz Sameen Shahgir, Ananya Gupta, Yue Dong, N. Benjamin Erichson
arXiv:2607. 19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions.
By Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria, Tasfia Nuzhat Ornee, Maleeha Sheikh
arXiv:2608.21775v1 Announce Type: new
Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From adver...
By Afshin Orojlooyjadid, Hitesh Patel
arXiv:2607. 00572v1 Announce Type: new Abstract: Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies.
By Shei Pern Chua, Fangzhao Wu
arXiv:2511. 00382v2 Announce Type: replace-cross Abstract: Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks.
By Mina Taraghi, Yann Pequignot, Amin Nikanjam, Mohamed Amine Merzouk, Foutse Khomh
arXiv:2606. 12702v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into clinical systems, making it essential to evaluate the real-world utility of these systems.
By Alyssa Unell, Miguel Fuentes, Brenna Li, Bridget Lin, Meena Jagadeesan, Sanmi Koyejo, Nigam Shah
arXiv:2606. 00160v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets.
By Junbo Zhang, Qianli Zhou, Xinyang Deng, Wen Jiang, Jie Pan, Jinbiao Zhu