2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDIFS-2.1
Paper Title IDENTIFYING PHYSICALLY REALIZABLE TRIGGERS FOR BACKDOORED FACE RECOGNITION NETWORKS
Authors Ankita Raj, Indian Institute of Technology Delhi, India; Ambar Pal, Johns Hopkins University, India; Chetan Arora, Indian Institute of Technology Delhi, India
SessionIFS-2: Information Forensics and Security
LocationArea K
Session Time:Monday, 20 September, 15:30 - 17:00
Presentation Time:Monday, 20 September, 15:30 - 17:00
Presentation Poster
Topic Information Forensics and Security: Multimedia forensics
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Backdoor attacks embed a hidden functionality into deep neural networks, causing the network to display anomalous behavior when activated by a predetermined pattern in the input (Trigger), while behaving well otherwise on public test data. Recent works have shown that backdoored face recognition (FR) systems can respond to natural-looking triggers like a particular pair of sunglasses. Such attacks pose a serious threat to the applicability of FR systems in high-security applications. We propose a novel technique to (1) detect whether an FR network is compromised with a natural, physically realizable trigger, and (2) identify such triggers given a compromised network. We demonstrate the effectiveness of our methods with a compromised FR network, where we are able to identify the trigger (e.g. green-sunglasses or red-bowtie) with a top-5 accuracy of 74%, whereas a naive brute force baseline achieves 56% accuracy.