Autonomous vehicles rely on sensors to measure road condition and make driving decisions, and their safety relies heavily on the reliability of these sensors. Out of all obstacle detection sensors, ultrasonic sensors have the largest market share and are expected to be increasingly installed on automobiles. Such sensors discover obstacles by emitting ultrasounds and analyzing their reflections. By exploiting the built-in vulnerabilities of sensors, we designed random spoofing, adaptive spoofing, and jamming attacks on ultrasonic sensors, and we managed to trick a vehicle to stop when it should keep moving, and let it fail to stop when it should. We validate our attacks on stand-alone sensors and moving vehicles, including a Tesla Model S with the ‘Autopilot’ system. The results show that the attacks cause blindness and malfunction of not only sensors but also autonomous vehicles, which can lead to collisions. To enhance the security of ultrasonic sensors and autonomous vehicles, we propose two defense strategies, single-sensor based Physical Shift Authentication (PSA) that verifies signals on the physical level, and Multiple Sensor Consistency Check (MSCC) that employs multiple sensors to verify signals on the system level. Our experiments on real sensors and MATLAB simulation reveal the validity of both schemes.

Voice assistants (VA) have become prevalent on a wide range of personal devices such as smartphones and smart speakers. As companies build voice assistants with extra functionalities, attacks that trick a voice assistant into performing malicious behaviors can pose a significant threat to a user’s security, privacy, and even safety. However, the diverse attacks and stand-alone defenses in the literature often lack a systematic perspective, making it challenging for designers to properly identify, understand, and mitigate the security threats against voice assistants. To overcome this problem, this article provides a thorough survey of the attacks and countermeasures for voice assistants. We systematize a broad category of relevant but seemingly unrelated attacks by the vulnerable system components and attack methods, and categorize existing countermeasures based on the defensive strategies from a system designer’s perspective. To assist designers in planning defense based on their demands, we provide a qualitative comparison of existing countermeasures by the implementation cost, usability, and security and propose practical suggestions. We envision this work can help build more reliability into voice assistants and promote research in this fast-evolving area.

Voice assistants (VAs) such as Siri and Google Now have become an increasingly popular human-machine interaction method and have made various systems voice controllable. Prior work on attacking voice assistants shows that the hidden voice commands that are incomprehensible to people can control the VAs. Hidden voice commands, though "hidden", are nonetheless audible. In this work, we design a completely inaudible attack, DolphinAttack, that modulates voice commands on ultrasonic carriers to achieve inaudibility. By leveraging the nonlinearity of the microphone circuits, the modulated low-frequency audio commands can be successfully demodulated, recovered, and more importantly interpreted by the voice assistants. We validate DolphinAttack on popular voice assistants, including Siri, Google Now, S Voice, HiVoice, Cortana, Alexa, etc. By injecting a sequence of inaudible voice commands, we show a few proof-of-concept attacks, which include activating Siri to initiate a FaceTime call on iPhone, activating Google Now to turn on the airplane mode, and even manipulating the navigation system in an Audi automobile. We propose hardware and software defense solutions. We validate that it is feasible to detect DolphinAttack by classifying the audios using supported vector machine (SVM), and suggest to re-design voice assistants to be resilient to inaudible voice command attacks.

Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals. Existing countermeasures largely focus on determining the genuineness of speech based on complete original audio recordings, which however often contain private content. This oversight may refrain deepfake detection from many applications, particularly in scenarios involving sensitive information like business secrets. In this paper, we propose SafeEar, a novel framework that aims to detect deepfake audios without relying on accessing the speech content within. Our key idea is to devise a neural audio codec into a novel decoupling model that well separates the semantic and acoustic information from audio samples, and only use the acoustic information (e.g., prosody and timbre) for deepfake detection. In this way, no semantic content will be exposed to the detector. To overcome the challenge of identifying diverse deepfake audio without semantic clues, we enhance our deepfake detector with real-world codec augmentation. Extensive experiments conducted on four benchmark datasets demonstrate SafeEar's effectiveness in detecting various deepfake techniques with an equal error rate (EER) down to 2.02%. Simultaneously, it shields five-language speech content from being deciphered by both machine and human auditory analysis, demonstrated by word error rates (WERs) all above 93.93% and our user study. Furthermore, our benchmark constructed for anti-deepfake and anti-content recovery evaluation helps provide a basis for future research in the realms of audio privacy preservation and deepfake detection.

Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexually explicit scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block sexually explicit content (e.g., naked) but may still be vulnerable to adversarial prompts-inputs that appear innocent but are ill-intended. In this paper, we present SafeGen, a framework to mitigate sexual content generation by text-to-image models in a text-agnostic manner. The key idea is to eliminate explicit visual representations from the model regardless of the text input. In this way, the text-to-image model is resistant to adversarial prompts since such unsafe visual representations are obstructed from within. Extensive experiments conducted on four datasets and large-scale user studies demonstrate SafeGen's effectiveness in mitigating sexually explicit content generation while preserving the high-fidelity of benign images. SafeGen outperforms eight state-of-the-art baseline methods and achieves 99.4% sexual content removal performance.

Automatic speaker recognition systems (SRSs) have been widely used in voice applications for personal identification and access control. A typical SRS consists of three stages, i.e., training, enrollment, and recognition. Previous work has revealed that SRSs can be bypassed by backdoor attacks at the training stage or by adversarial example attacks at the recognition stage. In this article, we propose Tuner, a new type of backdoor attack against the enrollment stage of SRS via adversarial ultrasound modulation, which is inaudible, synchronization-free, content-independent, and black-box. Our key idea is to first inject the backdoor into the SRS with modulated ultrasound when a legitimate user initiates the enrollment, and afterward, the polluted SRS will grant access to both the legitimate user and the adversary with high confidence. Our attack faces a major challenge of unpredictable user articulation at the enrollment stage. To overcome this challenge, we generate the ultrasonic backdoor by augmenting the optimization process with random speech content, vocalizing time, and volume of the user. Furthermore, to achieve real-world robustness, we improve the ultrasonic signal over traditional methods using sparse frequency points, precompensation, and single-sideband (SSB) modulation. We extensively evaluate Tuner on two common data sets and seven representative SRS models, as well as its robustness against seven kinds of defenses. Results show that our attack can successfully bypass SRSs while remaining effective to various speakers, speech content, etc. To mitigate this newly discovered threat, we also provide discussions on potential countermeasures, limitations, and future works of this new threat.