arXiv subjects

Tadayoshi Kohno

Publications and source records attributed to Tadayoshi Kohno.

41 records · Page 3Linked to original sources

arXiv2018

Computer Security Risks of Distant Relative Matching in Consumer Genetic Databases

Consumer genetic testing has become immensely popular in recent years and has lead to the creation of large scale genetic databases containing millions of dense autosomal genotype profiles. One of the most used features offered by genetic databases is the ability to find distant relatives using a technique called relative matching (or DNA matching). Recently, novel uses of relative matching were discovered that combined matching results with genealogical information to solve criminal cold cases. New estimates suggest that relative matching, combined with simple demographic information, could be used to re-identify a significant percentage of US Caucasian individuals. In this work we attempt to systematize computer security and privacy risks from relative matching and describe new security problems that can occur if an attacker uploads manipulated or forged genetic profiles. For example, forged profiles can be used by criminals to misdirect investigations, con-artists to defraud victims, or political operatives to blackmail opponents. We discuss solutions to mitigate these threats, including existing proposals to use digital signatures, and encourage the consumer genetics community to consider the broader security implications of relative matching now that it is becoming so prominent.

cs.CR↗

arXiv2018

Note on Attacking Object Detectors with Adversarial Stickers

Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are created such that, when provided to a deep learning algorithm, they are very likely to be mislabeled. This can be problematic when deep learning is used to assist in safety critical decisions. Recent research has shown that classifiers can be attacked by physical adversarial examples under various physical conditions. Given the fact that state-of-the-art objection detection algorithms are harder to be fooled by the same set of adversarial examples, here we show that these detectors can also be attacked by physical adversarial examples. In this note, we briefly show both static and dynamic test results. We design an algorithm that produces physical adversarial inputs, which can fool the YOLO object detector and can also attack Faster-RCNN with relatively high success rate based on transferability. Furthermore, our algorithm can compress the size of the adversarial inputs to stickers that, when attached to the targeted object, result in the detector either mislabeling or not detecting the object a high percentage of the time. This note provides a small set of results. Our upcoming paper will contain a thorough evaluation on other object detectors, and will present the algorithm.

cs.CR↗

arXiv2018

Challenges and New Directions in Augmented Reality, Computer Security, and Neuroscience -- Part 1: Risks to Sensation and Perception

Rapidly advancing AR technologies are in a unique position to directly mediate between the human brain and the physical world. Though this tight coupling presents tremendous opportunities for human augmentation, it also presents new risks due to potential adversaries, including AR applications or devices themselves, as well as bugs or accidents. In this paper, we begin exploring potential risks to the human brain from augmented reality. Our initial focus is on sensory and perceptual risks (e.g., accidentally or maliciously induced visual adaptations, motion-induced blindness, and photosensitive epilepsy), but similar risks may span both lower- and higher-level human brain functions, including cognition, memory, and decision-making. Though they have not yet manifested in practice in early-generation AR technologies, we believe that such risks are uniquely dangerous in AR due to the richness and depth with which it interacts with a user's experience of the physical world. We propose a framework, based in computer security threat modeling, to conceptually and experimentally evaluate such risks. The ultimate goal of our work is to aid AR technology developers, researchers, and neuroscientists to consider these issues before AR technologies are widely deployed and become targets for real adversaries. By considering and addressing these issues now, we can help ensure that future AR technologies can meet their full, positive potential.

cs.CR↗

arXiv2018

Robust Physical-World Attacks on Deep Learning Models

Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. Given that that emerging physical systems are using DNNs in safety-critical situations, adversarial examples could mislead these systems and cause dangerous situations.Therefore, understanding adversarial examples in the physical world is an important step towards developing resilient learning algorithms. We propose a general attack algorithm,Robust Physical Perturbations (RP2), to generate robust visual adversarial perturbations under different physical conditions. Using the real-world case of road sign classification, we show that adversarial examples generated using RP2 achieve high targeted misclassification rates against standard-architecture road sign classifiers in the physical world under various environmental conditions, including viewpoints. Due to the current lack of a standardized testing method, we propose a two-stage evaluation methodology for robust physical adversarial examples consisting of lab and field tests. Using this methodology, we evaluate the efficacy of physical adversarial manipulations on real objects. Witha perturbation in the form of only black and white stickers,we attack a real stop sign, causing targeted misclassification in 100% of the images obtained in lab settings, and in 84.8%of the captured video frames obtained on a moving vehicle(field test) for the target classifier.

cs.CR↗

arXiv2015

To Make a Robot Secure: An Experimental Analysis of Cyber Security Threats Against Teleoperated Surgical Robots

Teleoperated robots are playing an increasingly important role in military actions and medical services. In the future, remotely operated surgical robots will likely be used in more scenarios such as battlefields and emergency response. But rapidly growing applications of teleoperated surgery raise the question; what if the computer systems for these robots are attacked, taken over and even turned into weapons? Our work seeks to answer this question by systematically analyzing possible cyber security attacks against Raven II, an advanced teleoperated robotic surgery system. We identify a slew of possible cyber security threats, and experimentally evaluate their scopes and impacts. We demonstrate the ability to maliciously control a wide range of robots functions, and even to completely ignore or override command inputs from the surgeon. We further find that it is possible to abuse the robot's existing emergency stop (E-stop) mechanism to execute efficient (single packet) attacks. We then consider steps to mitigate these identified attacks, and experimentally evaluate the feasibility of applying the existing security solutions against these threats. The broader goal of our paper, however, is to raise awareness and increase understanding of these emerging threats. We anticipate that the majority of attacks against telerobotic surgery will also be relevant to other teleoperated robotic and co-robotic systems.

cs.RO↗