134 citations · 776 across the 124 of their papers we have counts for
18 papers · 1 filter
AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks
Thibaud Gloaguen, Robin Staab, Martin Vechev
With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Yet, recent progress in the field…
TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization
William Kalikman, Ivo Petrov, Dimitar I. Dimitrov +1
Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local. However, prior gradient i…
Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
Mark Vero, Fabian Kaczmarczyck, Ivan Petrov +6
Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They…
Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
Thibaud Gloaguen, Robin Staab, Mark Vero +1
With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such as user IDs or ti…
SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization
Hao Wang, Niels Mündler, Mark Vero +3
Reasoning language models (RLMs) are increasingly used in programming. Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabilities in generated code. Pri…
A Unified Framework for LLM Watermarks
Thibaud Gloaguen, Robin Staab, Nikola Jovanović +1
LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, e…
AutoBaxBuilder: Bootstrapping Code Security Benchmarking
Tobias von Arx, Niels Mündler, Mark Vero +2
As large language models (LLMs) see wide adoption in software engineering, the reliable assessment of the correctness and security of LLM-generated code is crucial. Notably, prior…
LLM Fingerprinting via Semantically Conditioned Watermarks
Thibaud Gloaguen, Robin Staab, Nikola Jovanović +1
Most LLM fingerprinting methods teach the model to respond to a few fixed queries with predefined atypical responses (keys). This memorization often does not survive common deploym…
Towards Watermarking of Open-Source LLMs
Thibaud Gloaguen, Nikola Jovanović, Robin Staab +1
While watermarks for closed LLMs have matured and have been included in large-scale deployments, these methods are not applicable to open-source models, which allow users full cont…
BaxBench: Can LLMs Generate Correct and Secure Backends?
Mark Vero, Niels Mündler, Victor Chibotaru +5
Automatic program generation has long been a fundamental challenge in computer science. Recent benchmarks have shown that large language models (LLMs) can effectively generate code…
Discovering Spoofing Attempts on Language Model Watermarks
Thibaud Gloaguen, Nikola Jovanović, Robin Staab +1
LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized thi…
Black-Box Adversarial Attacks on LLM-Based Code Completion
Slobodan Jenko, Niels Mündler, Jingxuan He +2
Modern code completion engines, powered by large language models (LLMs), assist millions of developers with their strong capabilities to generate functionally correct code. Due to…
Black-Box Detection of Language Model Watermarks
Thibaud Gloaguen, Nikola Jovanović, Robin Staab +1
Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of…
DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models
Berkay Berabi, Alexey Gronskiy, Veselin Raychev +3
The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semant…
Instruction Tuning for Secure Code Generation
Jingxuan He, Mark Vero, Gabriela Krasnopolska +1
Modern language models (LMs) have gained widespread acceptance in everyday and professional contexts, particularly in programming. An essential procedure enabling this adoption is…
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanović +1
Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. H…
Large Language Models for Code: Security Hardening and Adversarial Testing
Jingxuan He, Martin Vechev
Large language models (large LMs) are increasingly trained on massive codebases and used to generate code. However, LMs lack awareness of security and are found to frequently produ…
Securify: Practical Security Analysis of Smart Contracts
Petar Tsankov, Andrei Dan, Dana Drachsler Cohen +3
Permissionless blockchains allow the execution of arbitrary programs (called smart contracts), enabling mutually untrusted entities to interact without relying on trusted third par…