Eksplorasi makalah akademik, arsitektur sistem, dan implementasi kode.
# Breaking the Black Box: Understanding the Linear Nature of Adversarial Examples In the early days of deep learning, the emergence of "adversarial e...
# Beyond the Thermal Veil: Recovering Information via Multi-Time Correlations in Hawking Radiation **The Black Hole Information Paradox** has long be...
# Beyond PPO: Mastering Direct Preference Optimization (DPO) In the quest to align Large Language Models (LLMs) with human values, **Reinforcement Le...
# Efficient Machine Unlearning: A Deep Dive into the SISA Framework In the era of GDPR and the "Right to be Forgotten," the ability to remove a speci...
# Jailbroken: Understanding Why LLM Safety Training Fails **The cat-and-mouse game of AI safety is in full swing.** Every time a new guardrail is imp...
# Beyond the Neuron: Mastering Representation Engineering (RepE) for LLM Control In the quest to make Large Language Models (LLMs) transparent and co...
# Invisible Fingerprints: Mastering Tree-Ring Watermarking for Diffusion Models In the era of generative AI, the line between human-created art and m...
# Privacy-Preserving Deep Learning: A Deep Dive into DP-SGD In an era where data is the new oil, the tension between **model utility** and **user pri...
# Breaking the Guardrails: Understanding the Greedy Coordinate Gradient (GCG) Attack In the race to make Large Language Models (LLMs) safer, develope...
# Unmasking the Training Set: A Deep Dive into Membership Inference Attacks (MIA) Imagine you’ve deployed a state-of-the-art machine learning model t...