Search for: All records

IoT devices fundamentally lack built-in security mechanisms to protect themselves from security attacks. Existing works on improving IoT security mostly focus on detecting anomalous behaviors of IoT devices. However, these existing anomaly detection schemes may trigger an overwhelmingly large number of false alerts, rendering them unusable in detecting compromised IoT devices. In this paper we develop an effective and efficient framework, named CUMAD, to detect compromised IoT devices. Instead of directly relying on individual anomalous events, CUMAD aims to accumulate sufficient evidence in detecting compromised IoT devices, by integrating an autoencoder-based anomaly detection subsystem with a sequential probability ratio test (SPRT)-based sequential hypothesis testing subsystem. CUMAD can effectively reduce the number of false alerts in detecting compromised IoT devices, and moreover, it can detect compromised IoT devices quickly. Our evaluation studies based on the public-domain N-BaIoT dataset show that CUMAD can on average reduce the false positive rate from about 3.57% using only the autoencoder-based anomaly detection scheme to about 0.5%; in addition, CUMAD can detect compromised IoT devices quickly, with less than 5 observations on average. 

IoT devices fundamentally lack built-in security mechanisms to protect themselves from security attacks. Existing works on improving IoT security mostly focus on detecting anomalous behaviors of IoT devices. However, these existing anomaly detection schemes may trigger an overwhelmingly large number of false alerts, rendering them unusable in detecting compromised IoT devices. In this paper we develop an effective and efficient framework, named CUMAD, to detect compromised IoT devices. Instead of directly relying on individual anomalous events, CUMAD aims to accumulate sufficient evidence in detecting compromised IoT devices, by integrating an autoencoder-based anomaly detection subsystem with a sequential probability ratio test (SPRT)-based sequential hypothesis testing subsystem. CUMAD can effectively reduce the number of false alerts in detecting compromised IoT devices, and moreover, it can detect compromised IoT devices quickly. Our evaluation studies based on the public-domain N-BaIoT dataset show that CUMAD can on average reduce the false positive rate from about 3.57% using only the autoencoder-based anomaly detection scheme to about 0.5%; in addition, CUMAD can detect compromised IoT devices quickly, with less than 5 observations on average. 

Although some existing counterdrone measures can disrupt the invasion of certain consumer drone, to the best of our knowledge, none of them can accurately redirect it to a given location for defense. In this paper, we proposed a Drone Position Manipulation (DPM) attack to address this issue by utilizing the vulnerabilities of control and navigation algorithms used on consumer drones. As such drones usually depend on GPS for autopiloting, we carefully spoof GPS signals based on where we want to redirect a drone to, such that we indirectly affect its position estimates that are used by its navigation algorithm. By carefully manipulating these states, we make a drone gradually move to a path based on our requirements. This unique attack exploits the entire stack of sensing, state estimation, and navigation control together for quantitative manipulation of flight paths, different from all existing methods. In addition, we have formally analyzed the feasible range of redirected destinations for a given target. Our evaluation on open-source ArduPilot system shows that DPM is able to not only accurately lead a drone to a redirected destination but also achieve a large redirection range. 

We present a deep learning based solution for separating the direct and global light transport components from a single photograph captured under high frequency structured lighting with a co‐axial projector‐camera setup. We employ an architecture with one encoder and two decoders that shares information between the encoder and the decoders, as well as between both decoders to ensure a consistent decomposition between both light transport components. Furthermore, our deep learning separation approach does not require binary structured illumination, allowing us to utilize the full resolution capabilities of the projector. Consequently, our deep separation network is able to achieve high fidelity decompositions for lighting frequency sensitive features such as subsurface scattering and specular reflections. We evaluate and demonstrate our direct and global separation method on a wide variety of synthetic and captured scenes.