Author name cluster

Philipp Benz

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

UAI Conference 2023 Conference Paper

Noisy adversarial representation learning for effective and efficient image obfuscation

Jonghu Jeong
Minyong Cho
Philipp Benz
Tae-Hoon Kim

Recent real-world applications of deep learning have led to the development of machine learning as a service (MLaaS). However, the scenario of client-server inference presents privacy concerns, where the server processes raw data sent from the user’s client device. One solution to this issue is to provide an obfuscator function to the client device using Adversarial Representation Learning (ARL). Prior works have primarily focused on the privacy-utility trade-off while overlooking the computational cost and memory burden on the client side. In this paper, we propose an effective and efficient ARL method that incorporates feature noise into the ARL pipeline. We evaluated our approach on various datasets, comparing it with state-of-the-art ARL techniques. Our experimental results indicate that our method achieves better accuracy, lower computation and memory overheads, and improved resistance to information leakage and reconstruction attacks.

Details

IJCAI Conference 2021 Conference Paper

A Survey on Universal Adversarial Attack

Chaoning Zhang
Philipp Benz
Chenguo Lin
Adil Karjauv
Jing Wu
In So Kweon

The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i. e. a single perturbation to fool the target DNN for most images. With the focus on UAP against deep classifiers, this survey summarizes the recent progress on universal adversarial attacks, discussing the challenges from both the attack and defense sides, as well as the reason for the existence of UAP. We aim to extend this work as a dynamic survey that will regularly update its content to follow new works regarding UAP or universal attack in a wide range of domains, such as image, audio, video, text, etc. Relevant updates will be discussed at: https: //bit. ly/2SbQlLG. We welcome authors of future works in this field to contact us for including your new findings.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards a Fourier Perspective

Chaoning Zhang
Philipp Benz
Adil Karjauv
In So Kweon

The booming interest in adversarial attacks stems from a misalignment between human vision and a deep neural network (DNN), i. e. a human imperceptible perturbation fools the DNN. Moreover, a single perturbation, often called universal adversarial perturbation (UAP), can be generated to fool the DNN for most images. A similar misalignment phenomenon has also been observed in the deep steganography task, where a decoder network can retrieve a secret image back from a slightly perturbed cover image. We attempt explaining the success of both in a unified manner from the Fourier perspective. We perform task-specific and joint analysis and reveal that (a) frequency is a key factor that influences their performance based on the proposed entropy metric for quantifying the frequency distribution; (b) their success can be attributed to a DNN being highly sensitive to high-frequency content. We also perform feature layer analysis for providing deep insight on model generalization and robustness. Additionally, we propose two new variants of universal perturbations: (1) high-pass UAP (HP-UAP) being less visible to the human eye; (2) Universal Secret Adversarial Perturbation (USAP) that simultaneously achieves attack and hiding.

PDF Details

AAAI Conference 2020 Conference Paper

CD-UAP: Class Discriminative Universal Adversarial Perturbation

Chaoning Zhang
Philipp Benz
Tooba Imtiaz
In-So Kweon

A single universal adversarial perturbation (UAP) can be added to all natural images to change most of their predicted class labels. It is of high practical relevance for an attacker to have ﬂexible control over the targeted classes to be attacked, however, the existing UAP method attacks samples from all classes. In this work, we propose a new universal attack method to generate a single perturbation that fools a target network to misclassify only a chosen group of classes, while having limited inﬂuence on the remaining classes. Since the proposed attack generates a universal adversarial perturbation that is discriminative to targeted and non-targeted classes, we term it class discriminative universal adversarial perturbation (CD-UAP). We propose one simple yet effective algorithm framework, under which we design and compare various loss function conﬁgurations tailored for the class discriminative universal attack. The proposed approach has been evaluated with extensive experiments on various benchmark datasets. Additionally, our proposed approach achieves state-of-the-art performance for the original task of UAP attacking all classes, which demonstrates the effectiveness of our approach.

PDF Details

NeurIPS Conference 2020 Conference Paper

UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging

Chaoning Zhang
Philipp Benz
Adil Karjauv
Geng Sun
In So Kweon

Neural networks have been shown effective in deep steganography for hiding a full image in another. However, the reason for its success remains not fully clear. Under the existing cover ($C$) dependent deep hiding (DDH) pipeline, it is challenging to analyze how the secret ($S$) image is encoded since the encoded message cannot be analyzed independently. We propose a novel universal deep hiding (UDH) meta-architecture to disentangle the encoding of $S$ from $C$. We perform extensive analysis and demonstrate that the success of deep steganography can be attributed to a frequency discrepancy between $C$ and the encoded secret image. Despite $S$ being hidden in a cover-agnostic manner, strikingly, UDH achieves a performance comparable to the existing DDH. Beyond hiding one image, we push the limits of deep steganography. Exploiting its property of being \emph{universal}, we propose universal watermarking as a timely solution to address the concern of the exponentially increasing amount of images/videos. UDH is robust to a pixel intensity shift on the container image, which makes it suitable for challenging application of light field messaging (LFM). This is the first work demonstrating the success of (DNN-based) hiding a full image for watermarking and LFM. Code: \url{https: //github. com/ChaoningZhang/Universal-Deep-Hiding}

PDF Details

IROS Conference 2019 Conference Paper

Fast Perception, Planning, and Execution for a Robotic Butler: Wheeled Humanoid M-Hubo

Moonyoung Lee
Yujin Heo
Jinyong Park
Hyundae Yang
Ho-Deok Jang
Philipp Benz
Hyunsub Park
In-So Kweon

As the aging population grows at a rapid rate, there is an ever growing need for service robot platforms that can provide daily assistance at practical speed with reliable performance. In order to assist with daily tasks such as fetching a beverage, a service robot must be able to perceive its environment and generate corresponding motion trajectories. This becomes a challenging and computationally complex problem when the environment is unknown and thus the path planner must sample numerous trajectories that often are sub-optimal, extending the execution time. To address this issue, we propose a unique strategy of integrating a 3D object detection pipeline with a kinematically optimal manipulation planner to significantly increase speed performance at run-time. In addition, we develop a new robotic butler system for a wheeled humanoid that is capable of fetching requested objects at 24% of the speed a human needs to fulfill the same task. The proposed system was evaluated and demonstrated in a real-world environment setup as well as in public exhibition.

Details