The paper introduces CodeTracer, a forensic framework to trace malicious code completions back to the backdoor fine-tuning data.

This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.

The paper introduces a systematic benchmark to test LLMs' ability to recover Indicators of Compromise (IoCs) from JavaScript code, finding that while LLMs handle simple obfuscation well, encryption-ba…

The paper introduces CodeScan, a novel black-box framework that detects data poisoning in code generation LLMs by analyzing structural similarities across multiple generations to identify recurring, v…

The paper empirically evaluates the security quality of LLM-generated code across various prompting methods, finding that while prompting alters the structure of weaknesses, it is insufficient to reli…

The paper proposes a general, compiler-integrated framework for secure content composition that minimizes the syntactic difference between secure and insecure coding practices.

The paper introduces LeakDojo, a framework that systematically evaluates RAG leakage risks, finding that stronger LLM instruction-following and query generation are major independent contributors to d…

The paper organizes the first Poisoned Chalice of LLM Evaluation Competition to detect a large language model's prior exposure to training data without access to the full training corpus.

This paper identifies the 'Format-Reliability Gap'—where LLMs know about code vulnerabilities but generate insecure code anyway—and proposes a localized, per-vulnerability steering vector fix that sig…

The paper introduces the first byte-native Large Language Model (LLM) capable of analyzing raw executable binary data, achieving high accuracy in tasks like malware and architecture classification.

Minor, single-character perturbations to prompts can significantly degrade the security of code generated by LLMs, suggesting that prompt fragility is a major security concern beyond simple prompt inj…

The paper introduces ABLE, an LLM-based system that automatically generates YARA rules to bypass malware evasion checks in analysis sandboxes, achieving a 79% bypass success rate.

This paper analyzes various source-to-bytecode obfuscation techniques for Erlang, demonstrating that effective protection relies on exploiting the representational gaps between high-level semantics an…

The paper introduces LLM4CodeRE, a domain-adaptive LLM framework that significantly improves bidirectional code reverse engineering by unifying assembly-to-source and source-to-assembly translation.

The paper introduces Poison-with-Style (PwS), a stealthy model poisoning attack that exploits developers' inherent code styles as covert triggers to make Code LLMs generate vulnerable code without exp…

The paper introduces SEC-bench Pro, a rigorous benchmark for evaluating LLM-based bug hunting on complex software, finding that even advanced agents struggle with long-horizon security tasks.

The paper introduces Spaghetti Architect, a tool that generates controlled code datasets for machine learning models by deliberately adding redundancy, messiness, and difficulty.

The paper introduces SymTEE, an LLM-assisted symbolic execution framework that detects missing input validation vulnerabilities in TEE applications without needing complex, real TEE setups.

The paper introduces codebadger, a Model Context Protocol (MCP) server that integrates Joern's Code Property Graph (CPG) with LLMs, enabling large language models to perform large-scale, semantic prog…