Defensive AI Security Intern - Paris, France
Description
Apple's DRM stack protects media content and applications. Across the industry, external attackers increasingly use LLMs — interactively or via automated/agentic pipelines — to accelerate reverse-engineering of software protections; this is a general and growing trend, not specific to any one target. This internship addresses that trend directly: developing, from first principles, inputs that measurably perturb an LLM's internal state (activations, attention distributions, representation geometry) in ways that degrade its ability to usefully assist an attacker analyzing protected code/binaries.
This internship addresses that trend directly: developing, from first principles, inputs that measurably perturb an LLM's internal state (activations, attention distributions, representation geometry) in ways that degrade its ability to usefully assist an attacker analyzing protected code/binaries.
Minimum Qualifications
- Currently completing a Master's degree or enrolled in a PhD, in Computer Science, Applied Mathematics, or a related field, with strong theoretical grounding.
- Strong foundations in linear algebra, optimization (convex and non-convex), and probability/information theory, and ability to apply them to deep learning internals rather than just use libraries.
- Solid understanding of transformer architecture internals (attention mechanics, residual stream, embeddings) at a mathematical level.
- Hands-on experience with gradient-based adversarial attack techniques (FGSM/PGD-style methods, discrete optimization for token sequences, universal adversarial perturbations).
- Proficiency in Python and PyTorch, including writing custom gradient computations/hooks into model internals (not just using high-level APIs).
Preferred Qualifications
- Research experience in adversarial machine learning or mechanistic interpretability (activation patching, representation engineering, steering vectors).
- Familiarity with reverse engineering / binary analysis, to reason about what a real attacker workflow needs from the LLM.
- Coursework or research in spectral methods, information theory, or statistical learning theory applied to neural network analysis.
- Prior publications, competition results (e.g. adversarial ML challenges), or open-source contributions demonstrating this kind of mathematical adversarial ML work.
Skills
Sign in to read and join the discussion.