相关论文: Killing Stubborn Mutants with Symbolic Execution

Semiparametric language models (LMs) have shown promise in continuously learning from new text data by combining a parameterized neural LM with a growable non-parametric memory for memorizing new content. However, conventional…

We introduce stochastic activations. This novel strategy randomly selects between several non-linear functions in the feed-forward layer of a large language model. In particular, we choose between SILU or RELU depending on a Bernoulli draw.…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that induce LLMs to generate harmful content. Current methods…

In many modern LLM applications, such as retrieval augmented generation, prompts have become programs themselves. In these settings, prompt programs are repeatedly called with different user queries or data instances. A big practical…

Trusted Execution Environments (TEEs) provide hardware-enforced isolation that protects sensitive code and data from untrusted software. Despite their strong security guarantees, analyzing TEE applications remains challenging due to the…

We introduce $\mu$BERT, a mutation testing tool that uses a pre-trained language model (CodeBERT) to generate mutants. This is done by masking a token from the expression given as input and using CodeBERT to predict it. Thus, the mutants…

The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform basic security scans, they often fail to detect subtle…

Large Language Models (LLMs) have emerged as a promising alternative to traditional static program analysis methods, such as symbolic execution, offering the ability to reason over code directly without relying on theorem provers or SMT…

Standard representation probing for visual models relies on mathematically permutation-invariant operations like Global Average Pooling (GAP) or CLS tokens, treating patch representations as an unstructured bag-of-words. We challenge this…

Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…

Large Language Models (LLMs) struggle with complex reasoning due to limited diversity and inefficient search. We propose Soft Reasoning, an embedding-based search framework that optimises the embedding of the first token to guide…

Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. However, the high latency of autoregressive inference remains a…

Recently deep learning has dominated many machine learning areas, including spoken language understanding (SLU). However, deep learning models are notorious for being data-hungry, and the heavily optimized models are usually sensitive to…

Symbolic execution is a key technology in software testing, which generates test cases by collecting symbolic path constraints and then solving constraints with SMT solvers. Symbolic execution has been proven helpful in generating…

Model-based mutation analysis is a recent research area, and real-time system testing can benefit from using model mutants. Model-based mutation testing (MBMT) is a particular branch of model-based testing. It generates faulty versions of a…

Text-to-image synthesis models require the ability to generate diverse images while maintaining stability. To overcome this challenge, a number of methods have been proposed, including the collection of prompt-image datasets and the…

Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger…

A promising avenue for improving the effectiveness of behavioral-based malware detectors would be to combine fast traditional machine learning detectors with high-accuracy, but time-consuming deep learning models. The main idea would be to…

Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to increase the interpretability and explainability of black box Machine Learning (ML) algorithms. LIME typically generates an explanation for a single…

Memory corruption is a serious class of software vulnerabilities, which requires careful attention to be detected and removed from applications before getting exploited and harming the system users. Symbolic execution is a well-known method…