Related papers: Abstract Interpretation-Based Data Leakage Static …

Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast Internet-derived training corpora. To mitigate the risk of potential data contamination, LLM benchmarking has…

Machine learning (ML) explainability is central to algorithmic transparency in high-stakes settings such as predictive diagnostics and loan approval. However, these same domains require rigorous privacy guaranties, creating tension between…

Existing methods for explainable artificial intelligence (XAI), including popular feature importance measures such as SAGE, are mostly restricted to the batch learning scenario. However, machine learning is often applied in dynamic…

Abstraction is a powerful idea widely used in science, to model, reason and explain the behavior of systems in a more tractable search space, by omitting irrelevant details. While notions of abstraction have matured for deterministic…

This paper introduces an automatic debugging framework that relies on model-based reasoning techniques to locate faults in programs. In particular, model-based diagnosis, together with an abstract interpretation based conflict detection…

In a physical system, changing parameters such as temperature can induce a phase transition: an abrupt change from one state of matter to another. Analogous phenomena have recently been observed in large language models. Typically, the task…

In static analysis by abstract interpretation, one often uses widening operators in order to enforce convergence within finite time to an inductive invariant. Certain widening operators, including the classical one over finite polyhedra,…

The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…

Static security analysis is a widely used technique for detecting software vulnerabilities across a wide range of weaknesses, application domains, and programming languages. While prior work surveyed static analyzes for specific weaknesses…

Deep learning techniques applied to program analysis tasks such as code classification, summarization, and bug detection have seen widespread interest. Traditional approaches, however, treat programming source code as natural language text,…

Web applications continue to be a favorite target for hackers due to a combination of wide adoption and rapid deployment cycles, which often lead to the introduction of high impact vulnerabilities. Static analysis tools are important to…

Clinical natural language processing (NLP) models have shown promise for supporting hospital discharge planning by leveraging narrative clinical documentation. However, note-based models are particularly vulnerable to temporal and lexical…

Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new…

We introduce a privacy measure called pointwise maximal leakage, generalizing the pre-existing notion of maximal leakage, which quantifies the amount of information leaking about a secret $X$ by disclosing a single outcome of a (randomized)…

Large language models (LLMs) are increasingly used to generate requirements specifications, design documents, code, and test cases. In contrast, much less attention has been given to a more difficult assurance problem: statically verifying…

Machine learning (ML) has progressed rapidly during the past decade and the major factor that drives such development is the unprecedented large-scale data. As data generation is a continuous process, this leads to ML model owners updating…

In recent years, there has been significant progress in the development and industrial adoption of static analyzers. Such analyzers typically provide a large, if not huge, number of configurable options controlling the precision and…

Cryptographic research takes software timing side channels seriously. Approaches to mitigate them include constant-time coding and techniques to enforce such practices. However, recent attacks like Meltdown [42], Spectre [37], and…

The proliferation of automated data collection schemes and the advances in sensorics are increasing the amount of data we are able to monitor in real-time. However, given the high annotation costs and the time required by quality…

In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensitive information,…