AIBearisharXiv – CS AI · Jun 17/10
🧠Researchers demonstrate a novel adversarial attack using genetic algorithm-based prompt injection that can deceive LLM-powered reverse engineering tools like GhidraMCP into misinterpreting binary executables. This vulnerability exploits how large language models process decompiled code through surreptitious string variable assignments, potentially allowing malware to bypass automated detection systems that rely on AI-driven analysis.
AIBearisharXiv – CS AI · Jun 17/10
🧠Researchers have demonstrated that agentic AI systems used for software reverse engineering are vulnerable to prompt injection attacks embedded in executable binaries, and have developed both offensive obfuscation techniques and defensive detection methods. This research highlights critical security gaps in AI-powered code analysis tools that organizations are beginning to deploy in production environments.
AINeutralarXiv – CS AI · May 287/10
🧠Researchers reverse-engineered a Sokoban-playing RNN trained with model-free reinforcement learning and discovered that the network encodes planning strategies through specialized neural channels that represent directional movements and learned transition models. The findings demonstrate that neural networks can develop interpretable planning algorithms without explicit supervision, with path channels and extension kernels working together to implement bidirectional search and backtracking.
AIBearishDecrypt – AI · May 47/10
🧠A developer has created OpenMythos, an open-source project attempting to reverse-engineer Anthropic's unreleased Claude Mythos model, which the company has withheld due to concerning cyber-capabilities. The effort represents a broader trend of researchers probing safety boundaries in advanced AI systems through architectural reconstruction and public code releases.
🏢 Anthropic🧠 Claude
AI × CryptoNeutralarXiv – CS AI · Apr 77/10
🤖Researchers introduced CREBench, a benchmark to evaluate large language models' capabilities in cryptographic binary reverse engineering. The best-performing model (GPT-5.4) achieved 64.03% success rate, while human experts scored 92.19%, showing AI still lags behind human expertise in cryptographic analysis tasks.
🧠 GPT-5
AINeutralArs Technica – AI · Mar 107/10
🧠The article explores the legal complexities surrounding AI's ability to rewrite open source code and whether such modifications constitute legitimate reverse engineering or create derivative works that must comply with original licensing terms. This raises important questions about intellectual property rights and licensing obligations in AI-generated code.
AINeutralarXiv – CS AI · 6d ago6/10
🧠Researchers present a Quantitative Readability Score (QRS) framework that enables LLM agents to improve the readability of decompiled code while maintaining functional correctness. The approach combines structural similarity validation with three independent readability metrics (Lexical Surprisal, Structural Simplicity, and Idiomatic Quality) to guide code refinement without unintended optimization artifacts.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers have developed an end-to-end deep learning model that reconstructs CAD (Computer-Aided Design) models from point cloud data by segmenting objects into individual extrusions. This approach improves the generalization and robustness of AI models for reverse engineering and quality control applications across manufacturing industries.
AINeutralarXiv – CS AI · Apr 156/10
🧠Researchers propose CoDe-R, a two-stage framework using Large Language Models to improve binary decompilation by reducing logical errors and semantic misalignment. A 1.3B model using this approach achieves state-of-the-art performance on the HumanEval-Decompile benchmark, becoming the first lightweight model to exceed 50% re-executability rates.
AINeutralarXiv – CS AI · Apr 205/10
🧠Researchers demonstrate that Chain-of-Thought prompting significantly improves large language models' ability to deobfuscate control flow code, with GPT-5 achieving 16-20% performance gains over zero-shot prompting. The approach offers a potential alternative to expensive manual reverse engineering, though practical deployment remains limited to research benchmarks.
🧠 GPT-5
