Red Teaming GPT-4 Was Valuable. Violet Teaming Will Make It Better
To keep up with the speed of AI advances, we need to develop systems that use AI to defend public goods, too.
The Chemical Menace Inside Glaciers and Icebergs
Ice can trap pollutants and accelerate their breakdown, with troubling environmental consequences.
In Sudden Alarm, Tech Doyens Call for a Pause on ChatGPT
Tech luminaries, renowned scientists, and Elon Musk warn of an “out-of-control race” to develop and deploy ever-more-powerful AI systems.
Intel TDX Demystified: A Top-Down Approach. (arXiv:2303.15540v1 [cs.CR])
Intel Trust Domain Extensions (TDX) is a new architectural extension in the 4th Generation Intel Xeon Scalable Processor that supports confidential computing. TDX allows the deployment of virtual machines in…
Privacy-preserving machine learning for healthcare: open challenges and future perspectives. (arXiv:2303.15563v1 [cs.LG])
Machine Learning (ML) has recently shown tremendous success in modeling various healthcare prediction tasks, ranging from disease diagnosis and prognosis to patient treatment. Due to the sensitive nature of medical…
EMShepherd: Detecting Adversarial Samples via Side-channel Leakage. (arXiv:2303.15571v1 [cs.CR])
Deep Neural Networks (DNN) are vulnerable to adversarial perturbations-small changes crafted deliberately on the input to mislead the model for wrong predictions. Adversarial attacks have disastrous consequences for deep learning-empowered…
The Mirage of Breaking MIRAGE: Refuting the HPCA-2023 Paper “Are Randomized Caches Truly Random?”. (arXiv:2303.15673v1 [cs.AR])
The HPCA-2023 paper “Are Randomized Caches Truly Random?” makes the claim that “MIRAGE is broken” while relying on two faulty assumptions: (1) starting from a severely compromised initial state where…
Canary in Twitter Mine: Collecting Phishing Reports from Experts and Non-experts. (arXiv:2303.15847v1 [cs.CR])
The rise in phishing attacks via e-mail and short message service (SMS) has not slowed down at all. The first thing we need to do to combat the ever-increasing number…
Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm. (arXiv:2303.15901v1 [cs.LG])
Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with the initial…
A source separation approach to temporal graph modelling for computer networks. (arXiv:2303.15950v1 [cs.CR])
Detecting malicious activity within an enterprise computer network can be framed as a temporal link prediction task: given a sequence of graphs representing communications between hosts over time, the goal…