Search Results - "Vechev, Martin"

Reqomp: Space-constrained Uncomputation for Quantum Circuits by Paradis, Anouk, Bichsel, Benjamin, Vechev, Martin

“…Quantum circuits must run on quantum computers with tight limits on qubit and gate counts. To generate circuits respecting both limits, a promising opportunity…”
Get full text

Abstraqt: Analysis of Quantum Circuits via Abstract Stabilizer Simulation by Bichsel, Benjamin, Paradis, Anouk, Baader, Maximilian, Vechev, Martin

“…Stabilizer simulation can efficiently simulate an important class of quantum circuits consisting exclusively of Clifford gates. However, all existing…”
Get full text

AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation by Gehr, Timon, Mirman, Matthew, Drachsler-Cohen, Dana, Tsankov, Petar, Chaudhuri, Swarat, Vechev, Martin

“…We present AI 2 , the first sound and scalable analyzer for deep neural networks. Based on overapproximation, AI 2 can automatically prove safety properties…”
Get full text

VerX: Safety Verification of Smart Contracts by Permenev, Anton, Dimitrov, Dimitar, Tsankov, Petar, Drachsler-Cohen, Dana, Vechev, Martin

“…We present VerX, the first automated verifier able to prove functional properties of Ethereum smart contracts. VerX addresses an important problem as all…”
Get full text

ZeeStar: Private Smart Contracts by Homomorphic Encryption and Zero-knowledge Proofs by Steffen, Samuel, Bichsel, Benjamin, Baumgartner, Roger, Vechev, Martin

“…Data privacy is a key concern for smart contracts handling sensitive data. The existing work zkay addresses this concern by allowing developers without…”
Get full text

DP-Sniper: Black-Box Discovery of Differential Privacy Violations using Classifiers by Bichsel, Benjamin, Steffen, Samuel, Bogunovic, Ilija, Vechev, Martin

“…We present DP-Sniper, a practical black-box method that automatically finds violations of differential privacy.DP-Sniper is based on two key ideas: (i)…”
Get full text

From Principle to Practice: Vertical Data Minimization for Machine Learning by Staab, Robin, Jovanovic, Nikola, Balunovic, Mislav, Vechev, Martin

“…Aiming to train and deploy predictive models, organizations collect large amounts of detailed client data, risking the exposure of private information in the…”
Get full text

Robustness Certification for Point Cloud Models by Lorenz, Tobias, Ruoss, Anian, Balunovic, Mislav, Singh, Gagandeep, Vechev, Martin

“…The use of deep 3D point cloud models in safety-critical applications, such as autonomous driving, dictates the need to certify the robustness of these models…”
Get full text

Effective abstractions for verification under relaxed memory models by Dan, Andrei, Meshman, Yuri, Vechev, Martin, Yahav, Eran

“…We present a new abstract interpretation based approach for automatically verifying concurrent programs running on relaxed memory models. Our approach is based…”
Get full text

HLA I shield tumor skin T lymphocytes from NK-cell-mediated elimination by Chang, Yun-Tsan, Wolfensperger, Maya, Ignatova, Desislava, Kerl, Katrin, Hafner, Jürg, Dummer, Reinhard, French, Lars E., Cozzio, Antonio, Vechev, Martin, Guenova, Emmanuella

Get full text

Abstraction-guided synthesis of synchronization by Vechev, Martin, Yahav, Eran, Yorsh, Greta

“…We present a novel framework for automatic inference of efficient synchronization in concurrent programs, a task known to be difficult and error-prone when…”
Get full text

Large Language Models for Code: Security Hardening and Adversarial Testing by He, Jingxuan, Vechev, Martin

“…Large language models (large LMs) are increasingly trained on massive codebases and used to generate code. However, LMs lack awareness of security and are…”
Get full text

Efficient data race detection for async-finish parallelism by Raman, Raghavan, Zhao, Jisheng, Sarkar, Vivek, Vechev, Martin, Yahav, Eran

“…A major productivity hurdle for parallel programming is the presence of data races . Data races can lead to all kinds of harmful program behaviors, including…”
Get full text

A Unified Approach to Routing and Cascading for LLMs by Dekoninck, Jasper, Baader, Maximilian, Vechev, Martin

“…The widespread applicability of large language models (LLMs) has increased the availability of many fine-tuned models of various sizes targeting specific…”
Get full text

Multi-Neuron Unleashes Expressivity of ReLU Networks Under Convex Relaxation by Mao, Yuhao, Zhang, Yani, Vechev, Martin

“…Neural work certification has established itself as a crucial tool for ensuring the robustness of neural networks. Certification methods typically rely on…”
Get full text

AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs by Ünsal, Mert, Gehr, Timon, Vechev, Martin

“…We present the first correct-by-construction learning-based system for step-by-step mathematical integration. The key idea is to learn a policy, represented by…”
Get full text

Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation by Dekoninck, Jasper, Baader, Maximilian, Vechev, Martin

“…Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of large language models (LLMs). However, current…”
Get full text

CTBENCH: A Library and Benchmark for Certified Training by Mao, Yuhao, Balauca, Stefan, Vechev, Martin

“…Training certifiably robust neural networks is an important but challenging task. While many algorithms for (deterministic) certified training have been…”
Get full text

ConStat: Performance-Based Contamination Detection in Large Language Models by Dekoninck, Jasper, Müller, Mark Niklas, Vechev, Martin

“…Public benchmarks play an essential role in the evaluation of large language models. However, data contamination can lead to inflated performance, rendering…”
Get full text

Watermark Stealing in Large Language Models by Jovanović, Nikola, Staab, Robin, Vechev, Martin

“…LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit…”
Get full text