When LLMs are deployed in sensitive, human-facing settings, it is crucial that they do not output unsafe, biased, or privacy-violating outputs. For this reason, models are both trained and instructed to refuse to answer unsafe prompts such as ``Tell me how to build a bomb." We find that, despite these safeguards, it is possible to break model defenses simply by appending a space or other single character token to the end of a model's input. In a study of a variety of open-source models, we demonstrate that this simple perturbation is able to cause the majority of models to generate harmful outputs with very high probability. We further find that both Claude and GPT-3.5 demonstrate the same behavior. We examine the causes of this behavior, finding that the contexts in which single spaces occur in tokenized training data encourage models answer in lists or other formatted responses, overriding training signals to refuse unsafe requests. Our findings underscore the fragile state of current model alignment and promote the importance of developing more robust alignment methods.

Smart camera networks have recently emerged as a new class of sensor network infrastructure that is capable of supporting high-power in-network signal processing and enabling a wide range of applications. In this article, we provide an exposition of our efforts to build a low-bandwidth wireless camera network platform, called CITRIC, and its applications in smart camera networks. The platform integrates a camera, a microphone, a frequency-scalable (up to 624 MHz) CPU, 16 MB FLASH, and 64 MB RAM onto a single device. The device then connects with a standard sensor network mote to form a wireless camera mote. With reasonably low power consumption and extensive algorithmic libraries running on a decent operating system that is easy to program, CITRIC is ideal for research and applications in distributed image and video processing. Its capabilities of in-network image processing also reduce communication requirements, which has been high in other existing camera networks with centralized processing. Furthermore, the mote easily integrates with other low-bandwidth sensor networks via the IEEE 802.15.4 protocol. To justify the utility of CITRIC, we present several representative applications. In particular, concrete research results will be demonstrated in two areas, namely, distributed coverage hole identification and distributed object recognition.

Multi-carrier modulation receivers are susceptible to performance degradation due to intersymbol and intercarrier interference. We present a scheme that modifies the conventional single-tap frequency-domain equalizer into a multi-tap equalizer that can be used to cancel both intersymbol and intercarrier interference while preserving the function of the channel equalization. We demonstrate a method to obtain the optimal coefficients that maximizes the signal-to-noise ratio for each tone. The proposed scheme can be incorporated straightforwardly into conventional multi-carrier modulation receivers, while offering flexibility to allow tradeoff between performance and computation cost.