Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Reasoning

Although modern Large Language Models (LLMs) support extremely large contexts, their effectiveness in utilizing long context for code reasoning remains unclear. This paper investigates LLM reasoning ability over code snippets within large repositories and how it relates to their recall ability. Specifically, we differentiate between lexical code recall (verbatim retrieval) and semantic code recall (remembering what the code does). To measure semantic recall, we propose SemTrace, a code reasoning technique where the impact of specific statements on output is attributable and unpredictable. We also present a method to quantify semantic recall sensitivity in existing benchmarks. Our evaluation of state-of-the-art LLMs reveals a significant drop in code reasoning accuracy as a code snippet approaches the middle of the input context, particularly with techniques requiring high semantic recall like SemTrace. Moreover, we find that lexical recall varies by granularity, with models excelling at function retrieval but struggling with line-by-line recall. Notably, a disconnect exists between lexical and semantic recall, suggesting different underlying mechanisms. Finally, our findings indicate that current code reasoning benchmarks may exhibit low semantic recall sensitivity, potentially underestimating LLM challenges in leveraging in-context information.

XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants

AI coding assistants are widely used for tasks like code generation, bug detection, and comprehension. These tools now require large and complex contexts, automatically sourced from various origins$\unicode{x2014}$across files, projects, and contributors$\unicode{x2014}$forming part of the prompt fed to underlying LLMs. This automatic context-gathering introduces new vulnerabilities, allowing attackers to subtly poison input to compromise the assistant's outputs, potentially generating vulnerable code, overlooking flaws, or introducing critical errors. We propose a novel attack, Cross-Origin Context Poisoning (XOXO), that is particularly challenging to detect as it relies on adversarial code modifications that are semantically equivalent. Traditional program analysis techniques struggle to identify these correlations since the semantics of the code remain correct, making it appear legitimate. This allows attackers to manipulate code assistants into producing incorrect outputs, including vulnerabilities or backdoors, while shifting the blame to the victim developer or tester. We introduce a novel, task-agnostic black-box attack algorithm GCGS that systematically searches the transformation space using a Cayley Graph, achieving an 83.09% attack success rate on average across five tasks and eleven models, including GPT-4o and Claude 3.5 Sonnet v2 used by many popular AI coding assistants. Furthermore, existing defenses, including adversarial fine-tuning, are ineffective against our attack, underscoring the need for new security measures in LLM-powered coding tools.