Related papers: Abstract Interpretation-Based Data Leakage Static …
We present a new active model-learning approach to generating abstractions of a system implementation, as finite state automata (FSAs), from execution traces. Given an implementation and a set of observable system variables, the generated…
A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In…
Data collection for natural language (NL) understanding tasks has increasingly included human explanations alongside data points, allowing past works to introduce models that both perform a task and generate NL explanations for their…
Memory leaks are prevalent in various real-world software projects, thereby leading to serious attacks like denial-of-service. Though prior methods for detecting memory leaks made significant advance, they often suffer from low accuracy and…
Flaw-finding static analysis tools typically generate large volumes of code flaw alerts including many false positives. To save on human effort to triage these alerts, a significant body of work attempts to use machine learning to classify…
Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…
Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program…
In this paper, we show that knowledge distillation can be subverted to manipulate language model benchmark scores, revealing a critical vulnerability in current evaluation practices. We introduce "Data Laundering," a process that enables…
LIT-PCBA is widely used to benchmark virtual screening models, but our audit reveals that it is fundamentally compromised. We find extensive data leakage and molecular redundancy across its splits, including 2D-identical ligands within and…
The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning…
Automated machine learning techniques benefited from tremendous research progress in recently. These developments and the continuous-growing demand for machine learning experts led to the development of numerous AutoML tools. However, these…
Eliminating vulnerabilities from low-level code is vital for securing software. Static analysis is a promising approach for discovering vulnerabilities since it can provide developers early feedback on the code they write. But, it presents…
We introduce a tool that supports continuous flow analysis in order to detect security problems as the user edits. The tool uses abstract interpretation over both byte codes and abstract syntax trees to trace the flow of both type…
We study privacy leakage in the reasoning traces of large reasoning models used as personal agents. Unlike final outputs, reasoning traces are often assumed to be internal and safe. We challenge this assumption by showing that reasoning…
Static analyses aspire to explore all possible executions in order to achieve soundness. Yet, in practice, they fail to capture common dynamic behavior. Enhancing static analyses with dynamic information is a common pattern, with tools such…
Programs that process data that reside in files are widely used in varied domains, such as banking, healthcare, and web-traffic analysis. Precise static analysis of these programs in the context of software verification and transformation…
The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential…
Context: Static analyses are well-established to aid in understanding bugs or vulnerabilities during the development process or in large-scale studies. A low false-positive rate is essential for the adaption in practice and for precise…
Large language models (LLMs) are becoming more advanced and widespread and have shown their applicability to various domains, including cybersecurity. Static malware analysis is one of the most important tasks in cybersecurity; however, it…
Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model performance and explores strategies to mitigate these effects…