arXiv Machine Learning September 18, 2026 By Hyeongjun Choi, Wonyoung Jung, Haehoon Seo, Sungyup Nam

ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers

Read the original on arXiv Machine Learning →

The paper introduces ALIBI, a semantic cover story attack that injects a small, non-executed read‑only section into compiled binaries to mislead large language model (LLM) malware analyzers. By embedding a coherent but false security narrative, ALIBI can cause LLMs such as Gemini 2.5 Pro, GPT‑5.5 Pro, and Claude Opus 4.7 to downgrade or flip the verdicts of malicious samples. The attack also transfers to ELF binaries, and even a verification‑guided defense prompt only partially mitigates the effect, leaving a significant portion of malicious samples classified as benign.

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 Machine Learning.

arXiv AI

Jul 21

Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing

arXiv:2509. 14335v2 Announce Type: replace-cross Abstract: Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence.

By Xinran Zheng, Xingzhi Qian, Yiling He, Shuo Yang, Lorenzo Cavallaro

llms agents benchmarks

arXiv AI

Jun 19

Multi-View Decompilation for LLM-Based Malware Classification

arXiv:2606. 20436v1 Announce Type: cross Abstract: Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable.

By Bercan Turkmen, Vyas Raina

llms benchmarks

arXiv AI

Jul 2

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

arXiv:2607. 00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs).

By Junlong Liu, Haobo Wang, Weiqi Luo, Xiaojun Jia

llms benchmarks safety

arXiv Machine Learning

Jun 19

FloatDoor: Platform-Triggered Backdoors in LLMs

arXiv:2606. 19535v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts.

By Nils Loose, Jonas Sander, Felix M\"achtle, Thomas Eisenbarth

llms fine-tuning

arXiv AI

Aug 24

Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems

The paper introduces Trustworthy RAG, an evaluation agent designed to detect misinformation and knowledge poisoning in Retrieval-Augmented Generation systems. It combines natural language inference verification, a five-signal poison detector, and a weighted Trust Index to assess the reliability of retrieved content. Experiments on multiple LLMs show high accuracy and precision, with the agent effectively blocking unsafe advice in a secure-coding assistant scenario.

By Balkrishna Giri, Md Toufique Hasan, Jussi Rasku, Muhammad Waseem, Pekka Abrahamsson

llms rag agents

arXiv Computation and Language

Aug 27

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots

The paper introduces a three‑layer security framework designed to protect retrieval‑augmented generation (RAG) chatbots from both direct and indirect prompt injection attacks. Layer 1 filters user input with rule‑based patterns and a semantic anomaly classifier; Layer 2 enforces a provenance‑based instruction hierarchy during context assembly; Layer 3 audits model output with a policy rule engine and semantic drift detector. Evaluations on GPT‑4o, Llama 3, and Mistral 7B demonstrate a reduction in attack success rate from 71.4 % to 11.3 %, outperforming existing single‑layer defenses while keeping false positives low and latency acceptable.

By Gulshan Saleem, Nisar Ahmed, Muhammad Imran Zaman, Ali Hassan, Umar Mujahid

llms rag fine-tuning multimodal benchmarks safety

One email a morning, machine-written

Related stories

Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Multi-View Decompilation for LLM-Based Malware Classification

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

FloatDoor: Platform-Triggered Backdoors in LLMs

Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots