Side-channel analysis (SCA) poses a real-world threat by exploiting unintentional physical signals to extract secret information from secure devices. Evaluation labs also use the same techniques to certify device security. In recent years, deep learning has emerged as a prominent method for SCA, achieving state-ofthe-art attack performance at the cost of interpretability. Understanding how neural networks extract secrets is crucial for security evaluators aiming to defend against such attacks, as only by understanding the attack can one propose better countermeasures. In this work, we apply mechanistic interpretability to neural networks trained for SCA, revealing how models exploit what leakage in side-channel traces. We focus on sudden jumps in performance to reverse engineer learned representations, ultimately recovering secret masks and moving the evaluation process from blackbox to white-box. Our results show that mechanistic interpretability can scale to realistic SCA settings, even when relevant inputs are sparse, model accuracies are low, and side-channel protections prevent standard input interventions.

Many of the insights hitting soccer pitches today trace back to Jesse Davis and a team of computer scientists open-sourcing tools for some of the sport's trickiest problems. Imagine tuning in to the opening kickoff of a World Cup match and seeing a player intentionally send the ball all the way down the pitch and right out of bounds on the opponent's end. Casual fans might scratch their heads. If you were Jesse Davis, though, you'd know that this play could be a prime setup to score. Davis is a professor of computer science at KU Leuven in Belgium and head of its Sports Analytics Lab, which has been at the vanguard of a data awakening in soccer since its inception more than a decade ago. Though the research group brings machine-learning models to bear on a variety of sports--including basketball, volleyball, and field hockey--nowhere is its impact felt more than on the soccer pitch.

Each year the AAAI recognizes a group of individuals who have made significant, sustained contributions to the field of artificial intelligence by appointing them as Fellows. We're talking to some of the 2026 AAAI Fellows to find out more about their work. In this interview, we chat to Sanmay Das, who was elected as a Fellow . Could you start with a quick introduction, where you work, and your general area of research? Broadly speaking, I work in multiagent systems. I've done a lot of work at the intersection of AI and economics, and over the last decade or so I've thought a lot about projects in the AI for social impact and social good space. In particular, my interest has been in the allocation of scarce societal resources, thinking about how AI can be integrated, and what it tells us about systems where we don't necessarily want full free market resource allocation.

You probably wouldn't notice if an AI chatbot slipped ads into its responses Hundreds of millions of people consult artificial intelligence chatbots on a daily basis for everything from product recommendations to romance, making them a tempting audience to target with potentially below-the-radar advertising. Indeed, our research suggests AI chatbots could easily be used for covert advertising to manipulate their human users. We are computer scientists who have been tracking AI safety and privacy for several years. In a study we published in an Association for Computing Machinery journal, we found that chatbots trained to embed personalized product ads in replies to queries influenced people's choices about products. And most participants didn't recognize that they were being manipulated.

There's Never Been a Better Time to Study Computer Science Even as AI progresses, coders aren't doomed. It's a weird time to be studying computer science. Recent grads have a higher unemployment rate than those in just about every other major--yes, even philosophy. The internet is littered with rants from newly minted programmers who can't find work. On one such YouTube video, the top comment reads: "Your first mistake is not being born earlier."

Neural Information Processing Systems http://nips.cc/

L-CAD: Language-basedThe tricColorizationycle on the left is red, and the tricycle on the right is orange. We leverage a referring segmentation model to roughly estimate object contours mentioned in the ur description, which enables us to perform the instance-aware sampling strategy. Othe robustness of our model, we manually annotate a sequence of contours ranging from coarse to fine and visualize the corresponding colorization results. As shown in Figure 8, our model presents aG remarkable ability to produce condition-consistent colorization results even using imprecise contours. This is because the sampling is performed in the latent space using downsampled contours and the compression decoder in the pixel space could adaptively fix color bleeding issues.

Step 3: Given these S dispersed points T = {t1,t2,...,tS}as the seeds, we assign the neighboring pixels of each seed into the same part according to the Voronoi diagram and correspondingly derive S local parts.

Neural Information Processing Systems http://nips.cc/