arXiv subjects

Claudia Mamede

Publications and source records attributed to Claudia Mamede.

4 recordsLinked to original sources

arXiv2026

When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs

Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remains unclear. We analyze 8 code models spanning 6.7B-15B parameters on C programs using three datasets (DELTASECOMMITS, SVEN, and PRECISE-BUGS), comparing two diagnostic tasks on the same representations: identifying what patterns the code instantiates, and determining whether it is vulnerable. Models encode the first with high fidelity. Under the studied paired C-code datasets and linear-probing setup, vulnerability information is more accessible as a paired relational signal-whether code A is riskier than code B-than as a globally separable categorical label. This structural difference has implications for classification: the model reliably ranks which code is riskier but standard classifiers on isolated samples achieve limited accuracy because vulnerable and secure samples form overlapping distributions in representation space.

cs.CR↗

arXiv2026

Refusal Is Not Robustness: Measuring Harmful Reachability in Autoregressive Language Models

LLM safety evaluations via jailbreaking typically index on attack success rate (ASR): whether a generated response violates safeguards. However, ASR only evaluates sampled outputs and provides little information on the underlying generation process. Autoregressive language models define distributions over possible outputs, and a sampled refusal can coexist with substantial probability mass on harmful generation paths. We study this hidden structure through bounded continuation analysis (BCA), which models autoregressive generation as a stochastic process over token prefixes and computes the finite-horizon probability that generation reaches a harmful continuation. BCA constructs a bounded continuation tree, labels terminal continuations with a semantic harm evaluator, and estimates harmful reachability using exact probabilistic model checking. BCA complements ASR by measuring how much harmful behavior remains accessible beneath a sampled safe response. This makes it useful for distinguishing models that look identical under measured ASR values, and allocating red-team effort toward regions of the generation process with greater hidden risk. Across four instruction-tuned LLMs and 100 JailbreakBench behaviors, we show that BCA effectively quantifies hidden harmful behavior and provides a useful signal to guide red teaming.

cs.LG↗

arXiv2026

Are Sparse Autoencoders Useful for Java Function Bug Detection?

Software vulnerabilities such as buffer overflows and SQL injections are a major source of security breaches. Traditional methods for vulnerability detection remain essential but are limited by high false positive rates, scalability issues, and reliance on manual effort. These constraints have driven interest in AI-based approaches to automated vulnerability detection and secure code generation. While Large Language Models (LLMs) have opened new avenues for classification tasks, their complexity and opacity pose challenges for interpretability and deployment. Sparse Autoencoder offer a promising solution to this problem. We explore whether SAEs can serve as a lightweight, interpretable alternative for bug detection in Java functions. We evaluate the effectiveness of SAEs when applied to representations from GPT-2 Small and Gemma 2B, examining their capacity to highlight buggy behaviour without fine-tuning the underlying LLMs. We found that SAE-derived features enable bug detection with an F1 score of up to 89%, consistently outperforming fine-tuned transformer encoder baselines. Our work provides the first empirical evidence that SAEs can be used to detect software bugs directly from the internal representations of pretrained LLMs, without any fine-tuning or task-specific supervision. Code available at https://github.com/rufimelo99/SAE-Java-Bug-Detection

cs.SE↗

arXiv2025

Are Large Language Models Memorizing Bug Benchmarks?

Large Language Models (LLMs) have become integral to various software engineering tasks, including code generation, bug detection, and repair. To evaluate model performance in these domains, numerous bug benchmarks containing real-world bugs from software projects have been developed. However, a growing concern within the software engineering community is that these benchmarks may not reliably reflect true LLM performance due to the risk of data leakage. Despite this concern, limited research has been conducted to quantify the impact of potential leakage. In this paper, we systematically evaluate popular LLMs to assess their susceptibility to data leakage from widely used bug benchmarks. To identify potential leakage, we use multiple metrics, including a study of benchmark membership within commonly used training datasets, as well as analyses of negative log-likelihood and n-gram accuracy. Our findings show that certain models, in particular codegen-multi, exhibit significant evidence of memorization in widely used benchmarks like Defects4J, while newer models trained on larger datasets like LLaMa 3.1 exhibit limited signs of leakage. These results highlight the need for careful benchmark selection and the adoption of robust metrics to adequately assess models capabilities.

cs.SE↗