Search Results for author:
Found 20 papers, 11 papers with code
Manipulating Feature Visualizations with Gradient Slingshots
Deep Neural Networks (DNNs) are capable of learning complex and versatile representations, however, the semantic nature of the learned concepts remains unknown.
On the Detection of Image-Scaling Attacks in Machine Learning
Unfortunately, this preprocessing step is vulnerable to so-called image-scaling attacks where an attacker makes unnoticeable changes to an image so that it becomes a new image after scaling.
Learning Type Inference for Enhanced Dataflow Analysis
Comparing our approach against recent neural type inference systems, our model outperforms the current state-of-the-art by 7. 85% on the ManyTypes4TypeScript benchmark, achieving 71. 27% accuracy overall.
Ranked #1 on
Type prediction
on ManyTypes4TypeScript
Evil from Within: Machine Learning Backdoors through Hardware Trojans
In this paper, we challenge this assumption and introduce a backdoor attack that completely resides within a common hardware accelerator for machine learning.
No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning
In this paper, we show that this automation can be manipulated using adversarial learning.
I still know it's you! On Challenges in Anonymizing Source Code
We prove that the task of generating a $k$-anonymous program -- a program that cannot be attributed to one of $k$ authors -- is not computable in the general case.
Misleading Deep-Fake Detection with GAN Fingerprints
In particular, we show that an adversary can remove indicative artifacts, the GAN fingerprint, directly from the frequency spectrum of a generated image.
Machine Unlearning of Features and Labels
In this paper, we propose the first method for unlearning features and labels.
Dos and Don'ts of Machine Learning in Computer Security
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 different areas.
Against All Odds: Winning the Defense Challenge in an Evasion Competition with Diversification
Consequently, adversaries will also target the learning system and use evasion attacks to bypass the detection of malware.
Backdooring and Poisoning Neural Networks with Image-Scaling Attacks
By combining poisoning and image-scaling attacks, we can conceal the trigger of backdoors as well as hide the overlays of clean-label poisoning.
Evaluating Explanation Methods for Deep Learning in Security
Deep learning is increasingly used as a building block of security systems.
Misleading Authorship Attribution of Source Code using Adversarial Learning
In this paper, we present a novel attack against authorship attribution of source code.
Poisoning Behavioral Malware Clustering
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 antivirus systems.
Static Exploration of Taint-Style Vulnerabilities Found by Fuzzing
In this paper, we use static template matching to find recurrences of fuzzer-discovered vulnerabilities.
Cryptography and Security Programming Languages Software Engineering
Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection
To cope with the increasing variability and sophistication of modern attacks, machine learning has been widely adopted as a statistically-sound tool for malware detection.
Cryptography and Security
Fraternal Twins: Unifying Attacks on Machine Learning and Digital Watermarking
This problem has motivated the research field of adversarial machine learning that is concerned with attacking and defending learning methods.
From Malware Signatures to Anti-Virus Assisted Attacks
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 threats.
Cryptography and Security
When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries
Many distinguishing features present in source code, e. g. variable names, are removed in the compilation process, and compiler optimization may alter the structure of a program, further obscuring features that are known to be useful in determining authorship.
Cryptography and Security
Toward Supervised Anomaly Detection
Anomaly detection is being regarded as an unsupervised learning task as anomalies stem from adversarial or unlikely events with unknown distributions.
