Douglas Leith

The raw output of  a language neural net model is a set of probabilities over the possible next word (or token).  That is then converted into text output by a decoding step.  Standard decoding — greedy, beam search, or independent sampling — commits to each token or reasoning step without any lookahead about whether it’s … Read more

Classical mutation testing applies a small, fixed catalog of mutations to code, e.g. flipping + to – or changing True to False.  But this produces mutated code that often doesn’t resemble the kinds of mistakes real developers actually make.  In this project you will build a mutation-testing pipeline around a direct comparison: does learning to … Read more

Fine-tuning language models on sensitive text (medical notes, private messages, internal documents) risks the model memorizing and later regurgitating specifics from the training data — a well-documented failure mode for even small models. Differential privacy (DP), via DP-SGD, gives a formal, quantifiable guarantee against this by clipping per-example gradients and adding calibrated noise during training. … Read more

Plain Monte-Carlo Tree Search (MCTS) relies on random rollouts (simulations of future game moves) to estimate the value of a game position. AlphaZero’s key insight was to replace random rollouts with a learned neural network that biases the tree search toward promising moves, cutting the number of simulations needed for strong play.  In this project … Read more

Modern app traffic is almost universally encrypted (TLS/QUIC), so the payload itself reveals nothing to a passive observer. But metadata — packet sizes, timing, direction, burst structure — survives encryption untouched, and this metadata may leak surprising amounts of information about what’s actually happening on the device. In this project you will build, train, and … Read more