#AIOps #Research #Sec_code_review #Malware_analysis "CogniCrypt: Synergistic Directed Execution and LLM-Driven Analysis for Zero-Day AI-Generated Malware Detection", Mar. 2026. ]-> CogniCrypt Prototype (Repo) github.com/DrEslamimehr/C… // The weaponization of LLMs for automated malware generation poses an existential threat to conventional detection paradigms. AI-generated malware exhibits polymorphic, metamorphic, and context-aware evasion capabilities that render signature-based and shallow heuristic defenses obsolete

#AIOps #Sec_code_review "ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code", Mar. 2026. github.com/elzobrito/ESAA… // ESAA-Security, a domain-specific specialization of ESAA for agentassisted security auditing of software repositories, with particular emphasis on AI-generated or AI-modified code. The framework produces structured check results, vulnerability inventories, severity classifications, risk matrices, remediation guidance, executive summaries, and a final audit report

#MLSecOps #Sec_code_review "SecCodeBench-V2 Technical Report", Feb. 2026. // SecCodeBench-V2 (SCBv2) - github.com/alibaba/sec-co… benchmark for evaluating LLM copilots’ capabilities of generating secure code. SCBv2 adopts a function-level task formulation: each scenario provides a complete project scaffold and requires the model to implement or patch a designated target function under fixed interfaces and dependencies. For each scenario, SCBv2 provides executable PoC test cases for both functional validation and security verification. All test cases are authored and double-reviewed by security experts, ensuring high fidelity, broad coverage, and reliable ground truth

#tools #Sec_code_review "Uncovering Hidden Inclusions of Vulnerable Dependencies in Real-World Java Projects", Jan 2026. // We present Unshade tool github.com/stschott/unsha… - hybrid approach towards dependency scanning in Java that combines the efficiency of metadata-based scanning with the ability to detect modified dependencies of code-centric approaches

#tools #Sec_code_review #Offensive_security Claude Code in a devcontainer github.com/trailofbits/cl… // Sandboxed devcontainer for running Claude Code in bypass mode safely. Built for security audits and untrusted code review

#reversing #Kernel_Security #Sec_code_review Exploiting Reversing (ER) series: Part 1 - Windows kernel drivers (1) exploitreversing.com/2023/04/11/exp… Part 2 - Windows kernel drivers (2) exploitreversing.com/2024/01/03/exp… Part 3 - Chrome exploitreversing.com/2025/01/22/exp… Part 4 - macOS/iOS exploitreversing.com/2025/02/04/exp… Part 5 - Hyper-V exploitreversing.com/2025/03/12/exp… // step-by-step research series on Windows, macOS, hypervisors and browsers

#Analytics #Sec_code_review Top-10 C and C++ Errors of 2025 pvs-studio.com/en/blog/posts/… See also: ]-> Top-10 noteworthy Java errors in 2025 - pvs-studio.com/en/blog/posts/… ]-> Top-10 errors found in C# projects in 2025 - pvs-studio.com/en/blog/posts/…

#tools #Research #Sec_code_review "AutoBaxBuilder: Bootstrapping Code Security Benchmarking", Dec.2025. ]-> github.com/eth-sri/autoba… // We introduce a robust pipeline with fine-grained plausibility checks, leveraging the code understanding capabilities of LLMs to construct functionality tests and end-to-end security-probing exploits

#Research #Sec_code_review #Threat_Research "A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection", Dec.2025. ]-> github.com/oxygen-hunter/… // We provide a structured systematization of obfuscation techniques and evaluate them under a unified framework. Specifically, we categorize existing obfuscation methods into three major classes (layout, data flow, and control flow) covering 11 subcategories and 19 techniques. We implement these techniques across four programming languages (Solidity, C, C++, Python) using a consistent LLM-driven approach, and evaluate their effects on 15 LLMs spanning four model families (DeepSeek, OpenAI, Qwen, LLaMA), as well as on two coding agents (GitHub Copilot and Codex). Our findings reveal both positive and negative impacts of code obfuscation on LLM-based vulnerability detection, highlighting conditions under which obfuscation leads to performance improvements or degradations

#tools #Sec_code_review "InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution", Nov. 2025. ]-> github.com/Tokfinity/InfC… // InfCode is an adversarial multi-agent Code Agent System which uses LLMs to automatically analyze and fix Code Repo issues

#tools #Sec_code_review "Distilling Lightweight Language Models for C/C++ Vulnerabilities", Oct. 2025. ]-> github.com/yangxiaoxuan12… // This paper presents FineSec - framework that harnesses LLMs through knowledge distillation to enable efficient and precise vulnerability identification in C/C++ codebases. FineSec utilizes knowledge distillation to transfer expertise from large teacher models to compact student models, achieving high accuracy with minimal computational cost. Extensive evaluations on C/C++ codebases demonstrate its superiority over both base models and larger LLMs in identifying complex vulnerabilities and logical flaws

#tools #Sec_code_review "KNighter: Transforming Static Analysis with LLM-Synthesized Checkers", SOSP 2025. ]-> github.com/ise-uiuc/KNigh… // KNighter - first approach that unlocks scalable LLM-based static analysis by automatically synthesizing static analyzers from historical bug patterns. Rather than using LLMs to directly analyze massive systems, our key insight is leveraging LLMs to generate specialized static analyzers guided by historical patch knowledge. This work establishes an entirely new paradigm for scalable, reliable, and traceable LLM-based static analysis for real-world systems via checker synthesis

#tools #Sec_code_review "ConfLogger: Enhance Systems' Configuration Diagnosability through Configuration Logging", 2025. ]-> ConfLogger code repository - github.com/shanshw/ConfLo… // ConfLogger - first tool that unifies configuration-aware static taint analysis with LLM-based log generation to enhance software configuration diagnosability

#Sec_code_review "AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution",  2025. ]-> All implementation details and datasets - github.com/UzL-ITS/AutoSt… // In this work, we propose a novel approach to automatically generate symbolic stubs for external functions during symbolic execution that leverages Genetic Programming

#Research #Sec_code_review "PurpCode: Reasoning for Safer Code Generation", 2025. ]-> github.com/purpcode-uiuc/… ]-> huggingface.co/purpcode // the first post-training recipe for training safe code reasoning models towards generating secure code and defending against malicious cyberactivities

#Research #Sec_code_review "Explainable Vulnerability Detection in C/C++ Using Edge-Aware Graph Attention Networks", 2025. ]-> github.com/Radowan98/Expl… // This paper presents ExplainVulD, a graph-based framework for vulnerability detection in C/C++ code. The method constructs Code Property Graphs and represents nodes using dual-channel embeddings that capture both semantic and structural information. These are processed by an edge-aware attention mechanism that incorporates edge-type embeddings to distinguish among program relations

#Sec_code_review "FuncVul: An Effective Function Level Vulnerability Detection Model using LLM and Code Chunk", 2025. ]-> Repo: github.com/sajalhalder/Fu…

#Sec_code_review "CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection", 2025. ]-> github.com/CASTLE-Benchma…

#Research #Sec_code_review "TYPEPULSE: Detecting Type Confusion Bugs in Rust Programs", 2025. ]-> zenodo.org/records/147501…