arXiv subjects

Aniruddha Saha

Publications and source records attributed to Aniruddha Saha.

21 records · Page 2Linked to original sources

arXiv2020

Role of Spatial Context in Adversarial Robustness for Object Detection

The benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per image which means they implicitly use contextual reasoning for their predictions. However, one can show that an adversary can design adversarial patches which do not overlap with any objects of interest in the scene and exploit contextual reasoning to fool standard detectors. In this paper, we examine this problem and design category specific adversarial patches which make a widely used object detector like YOLO blind to an attacker chosen object category. We also show that limiting the use of spatial context during object detector training improves robustness to such adversaries. We believe the existence of context based adversarial attacks is concerning since the adversarial patch can affect predictions without being in vicinity of any objects of interest. Hence, defending against such attacks becomes challenging and we urge the research community to give attention to this vulnerability.

cs.CV↗

arXiv2019

Hidden Trigger Backdoor Attacks

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on deep networks where the attacker provides poisoned data to the victim to train the model with, and then activates the attack by showing a specific small trigger pattern at the test time. Most state-of-the-art backdoor attacks either provide mislabeled poisoning data that is possible to identify by visual inspection, reveal the trigger in the poisoned data, or use noise to hide the trigger. We propose a novel form of backdoor attack where poisoned data look natural with correct labels and also more importantly, the attacker hides the trigger in the poisoned data and keeps the trigger secret until the test time. We perform an extensive study on various image classification settings and show that our attack can fool the model by pasting the trigger at random locations on unseen images although the model performs well on clean data. We also show that our proposed attack cannot be easily defended using a state-of-the-art defense algorithm for backdoor attacks.

cs.CV↗

arXiv2019

Universality in coalescence of polymeric fluid drops

Coalescence of liquid droplets involves an interplay between capillary forces, viscous forces and inertial forces. Here, we unveil a universal temporal evolution of the neck radius during the coalescence of two polymeric drops. Through high speed imaging we demonstrate that drops of polyacrylamide (PAM), poly-vinyl alcohol (PVA), polyethylene oxide (PEO), polyethylene glycol (PEG) and xanthan gum (XG) depict a universal behavior $R/\sqrt(ν_0λ) \sim (t/λ)^{0.36}(C/C^{*})^{-0.83}$ over a dilute, semi-dilute and non-dilute range of concentrations. A linear Phan-Thein-Tanner viscoelastic model captures the temporal aspect of universality.

physics.flu-dyn↗