Search Results for author:
Found 21 papers, 13 papers with code
Buffer-free Class-Incremental Learning with Out-of-Distribution Detection
In this paper, we present an in-depth analysis of post-hoc OOD detection methods and investigate their potential to eliminate the need for a memory buffer.
Security Benefits and Side Effects of Labeling AI-Generated Images
Assuming that simplicity, transparency, and trust are likely to impact the successful adoption of such labels, we first qualitatively explore users' opinions and expectations of AI labeling using five focus groups.
Rethinking Robustness in Machine Learning: A Posterior Agreement Approach
The robustness of algorithms against covariate shifts is a fundamental problem with critical implications for the deployment of machine learning algorithms in the real world.
Fake It Until You Break It: On the Adversarial Robustness of AI-generated Image Detectors
While generative AI (GenAI) offers countless possibilities for creative and productive tasks, artificially generated media can be misused for fraud, manipulation, scams, misinformation campaigns, and more.
Prompt Obfuscation for Large Language Models
Overall, we demonstrate that prompt obfuscation is an effective mechanism to safeguard the intellectual property of a system prompt while maintaining the same utility as the original prompt.
HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data
The data synthesis pipeline generates pairs of vulnerable and fixed codes for specific Common Weakness Enumeration (CWE) types by utilizing a state-of-the-art LLM for repairing vulnerable code.
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in the LLM system prompt.
Whispers in the Machine: Confidentiality in LLM-integrated Systems
Large Language Models (LLMs) are increasingly augmented with external tools and commercial services into LLM-integrated systems.
$σ$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging.
A Representative Study on Human Detection of Artificially Generated Media Across Countries
To further understand which factors influence people's ability to detect generated media, we include personal variables, chosen based on a literature review in the domains of deepfake and fake news research.
Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
The fundamental task of negotiation spans many key features of communication, such as cooperation, competition, and manipulation potentials.
On the Limitations of Model Stealing with Uncertainty Quantification Models
We realize that during training, the models tend to have similar predictions, indicating that the network diversity we wanted to leverage using uncertainty quantification models is not (high) enough for improvements on the model stealing task.
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models
We evaluate the effectiveness of our approach by examining code language models in generating high-risk security weaknesses.
WaveFake: A Data Set to Facilitate Audio Deepfake Detection
Deep generative modeling has the potential to cause significant harm to society.
Dompteur: Taming Audio Adversarial Examples
In this paper we propose a different perspective: We accept the presence of adversarial examples against ASR systems, but we require them to be perceivable by human listeners.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
VenoMave: Targeted Poisoning Against Speech Recognition
In a more realistic scenario, when the target audio waveform is played over the air in different rooms, VENOMAVE maintains a success rate of up to 73. 3%.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification
The neural networks for uncertainty quantification simultaneously diminish the vulnerability to the attack, which is reflected in a lower recognition accuracy of the malicious target text in comparison to a standard hybrid ASR system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Leveraging Frequency Analysis for Deep Fake Image Recognition
Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.
Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems
In this paper, we demonstrate the first algorithm that produces generic adversarial examples, which remain robust in an over-the-air attack that is not adapted to the specific environment.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding
We use this backpropagation to learn the degrees of freedom for the adversarial perturbation of the input signal, i. e., we apply a psychoacoustic model and manipulate the acoustic signal below the thresholds of human perception.
Cryptography and Security Sound Audio and Speech Processing
