24 citations · 70 across the 16 of their papers we have counts for
17 papers
Anti-Backdoor Coreset Selection via Cumulative Entropy
Qi Zhao, Christian Wressnegger
Recent training-time defenses against neural backdoors isolate a benign subset from poisoned training data, to learn a backdoor-free model from it. In this paper, we formulate this…
Rising From the Ashes: How Agentic AI is Unblocking Challenges in Cybersecurity
Gabriela F. Ciocarlie, Kathrin Grosse, Somesh Jha +3
Security remains a high-cost challenge, with many problems historically deemed inefficient to address or effectively unsolvable. A significant number of these problems stem from la…
Chasing Shadows: Pitfalls in LLM Security Research
Jonathan Evertz, Niklas Risse, Nicolai Neuer +12
Large language models (LLMs) are increasingly prevalent in security research. Their unique characteristics, however, introduce challenges that undermine established paradigms of re…
S2AP: Score-space Sharpness Minimization for Adversarial Pruning
Giorgio Piras, Qi Zhao, Fabio Brau +3
Adversarial pruning methods have emerged as a powerful tool for compressing neural networks while preserving robustness against adversarial attacks. These methods typically follow…
Controlling Latent Diffusion Using Latent CLIP
Jason Becker, Chris Wendler, Peter Baylies +2
Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more effic…
Holistic Adversarially Robust Pruning
Qi Zhao, Christian Wressnegger
Neural networks can be drastically shrunk in size by removing redundant parameters. While crucial for the deployment on resource-constraint hardware, oftentimes, compression comes…
Generalized Adversarial Code-Suggestions: Exploiting Contexts of LLM-based Code-Completion
Karl Rubel, Maximilian Noppel, Christian Wressnegger
While convenient, relying on LLM-powered code assistants in day-to-day work gives rise to severe attacks. For instance, the assistant might introduce subtle flaws and suggest vulne…
Backdooring Explainable Machine Learning
Maximilian Noppel, Lukas Peter, Christian Wressnegger
Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanat…
Machine Unlearning of Features and Labels
Alexander Warnecke, Lukas Pirch, Christian Wressnegger +1
Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such…
LaserShark: Establishing Fast, Bidirectional Communication into Air-Gapped Systems
Niclas Kühnapfel, Stefan Preußler, Maximilian Noppel +3
Physical isolation, so called air-gapping, is an effective method for protecting security-critical computers and networks. While it might be possible to introduce malicious code th…
Dos and Don'ts of Machine Learning in Computer Security
Daniel Arp, Erwin Quiring, Feargus Pendlebury +5
With the growing processing power of computing systems and the increasing availability of massive datasets, machine learning algorithms have led to major breakthroughs in many diff…
Aim Low, Shoot High: Evading Aimbot Detectors by Mimicking User Behavior
Tim Witschel, Christian Wressnegger
Current schemes to detect cheating in online games often build on the assumption that the applied cheat takes actions that are drastically different from normal behavior. For insta…
Political Elections Under (Social) Fire? Analysis and Detection of Propaganda on Twitter
Ansgar Kellner, Lisa Rangosch, Christian Wressnegger +1
For many, social networks have become the primary source of news, although the correctness of the provided information and its trustworthiness are often unclear. The investigations…
Evaluating Explanation Methods for Deep Learning in Security
Alexander Warnecke, Daniel Arp, Christian Wressnegger +1
Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machi…
Poisoning Behavioral Malware Clustering
Battista Biggio, Konrad Rieck, Davide Ariu +4
Clustering algorithms have become a popular tool in computer security to analyze the behavior of malware variants, identify novel malware families, and generate signatures for anti…
Web-based Cryptojacking in the Wild
Marius Musch, Christian Wressnegger, Martin Johns +1
With the introduction of memory-bound cryptocurrencies, such as Monero, the implementation of mining code in browser-based JavaScript has become a worthwhile alternative to dedicat…
From Malware Signatures to Anti-Virus Assisted Attacks
Christian Wressnegger, Kevin Freeman, Fabian Yamaguchi +1
Although anti-virus software has significantly evolved over the last decade, classic signature matching based on byte patterns is still a prevalent concept for identifying security…