38 citations · 64 across the 23 of their papers we have counts for
23 papers
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Yu-Du Feng, Niels Mündler-Sasahara, Mark Vero +1
Reasoning language models (RLMs) demonstrate impressive performance by leveraging test-time compute in the form of reasoning tokens. However, this behavior makes adapting RLMs to n…
Widening the Gap: Exploiting LLM Quantization via Outlier Injection
Xiaohua Zhan, Kazuki Egashira, Robin Staab +2
LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a…
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…
Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR
Kazuki Egashira, Mark Vero, Jasper Dekoninck +3
Reinforcement Learning with Verifiable Rewards (RLVR) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs). While RLVR is designe…
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…
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…
Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation
Giovanni De Muri, Mark Vero, Robin Staab +1
LLMs are often used by downstream users as teacher models for knowledge distillation, compressing their capabilities into memory-efficient models. However, as these teacher models…
Fewer Weights, More Problems: A Practical Attack on LLM Pruning
Kazuki Egashira, Robin Staab, Thibaud Gloaguen +2
Model pruning, i.e., removing a subset of model weights, has become a prominent approach to reducing the memory footprint of large language models (LLMs) during inference. Notably,…
Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
Thibaud Gloaguen, Mark Vero, Robin Staab +1
Finetuning open-weight Large Language Models (LLMs) is standard practice for achieving task-specific performance improvements. Until now, finetuning has been regarded as a controll…
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…
COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
Philipp Guldimann, Alexander Spiridonov, Robin Staab +9
The EU's Artificial Intelligence Act (AI Act) is a significant step towards responsible AI development, but lacks clear technical interpretation, making it difficult to assess mode…
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…
A Synthetic Dataset for Personal Attribute Inference
Hanna Yukhymenko, Robin Staab, Mark Vero +1
Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowled…
Back to the Drawing Board for Fair Representation Learning
Angéline Pouget, Nikola Jovanović, Mark Vero +2
The goal of Fair Representation Learning (FRL) is to mitigate biases in machine learning models by learning data representations that enable high accuracy on downstream tasks while…
Exploiting LLM Quantization
Kazuki Egashira, Mark Vero, Robin Staab +2
Quantization leverages lower-precision weights to reduce the memory usage of large language models (LLMs) and is a key technique for enabling their deployment on commodity hardware…
Private Attribute Inference from Images with Vision-Language Models
Batuhan Tömekçe, Mark Vero, Robin Staab +1
As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has pr…
Large Language Models are Advanced Anonymizers
Robin Staab, Mark Vero, Mislav Balunović +1
Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing…
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…
Beyond Memorization: Violating Privacy Via Inference with Large Language Models
Robin Staab, Mark Vero, Mislav Balunović +1
Current privacy research on large language models (LLMs) primarily focuses on the issue of extracting memorized training data. At the same time, models' inference capabilities have…
CuTS: Customizable Tabular Synthetic Data Generation
Mark Vero, Mislav Balunović, Martin Vechev
Privacy, data quality, and data sharing concerns pose a key limitation for tabular data applications. While generating synthetic data resembling the original distribution addresses…
TabLeak: Tabular Data Leakage in Federated Learning
Mark Vero, Mislav Balunović, Dimitar I. Dimitrov +1
While federated learning (FL) promises to preserve privacy, recent works in the image and text domains have shown that training updates leak private client data. However, most high…
Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering
Thorir Mar Ingolfsson, Mark Vero, Xiaying Wang +3
The computational demands of neural architecture search (NAS) algorithms are usually directly proportional to the size of their target search spaces. Thus, limiting the search to h…