• FAQ
  • Docs
  • Jobs
  • Contact
  • FAQ
  • Docs
  • Jobs
  • Contact
Get Started

Copyright Β© 2026 SpeedyApply. All rights reserved.

GitHubLinkedInDiscordDiscordTikTok

Resources

ContactFAQBlogAffiliate

Legal

Privacy PolicyTerms of Service

Chrome Web StoreEdge Add-onsAdd-ons for Firefox
  • FAQ
  • Docs
  • Jobs
  • Contact
  • FAQ
  • Docs
  • Jobs
  • Contact
Get Started

Defensive AI Security Intern

Apple β€’ Paris, France

A
Apple

Defensive AI Security Intern

AI / MLInternshipParis, France6 days ago

Summary

Apple's DRM stack protects media content and applications. Across the industry, external attackers increasingly use LLMs β€” interactively or via automated/agentic pipelines β€” 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.

Description

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.

Responsibilities

  • Formulate the problem mathematically: define what "confusion" or degraded internal state means in terms of measurable quantities (activation/representation drift, attention entropy, logit distribution shift, loss landscape behavior) rather than qualitative output judgments.
  • Develop gradient-based and optimization-based methods for crafting adversarial inputs (e.g. embedding-space perturbation, discrete token optimization Γ  la GCG/greedy coordinate search, universal adversarial triggers) targeting the internal-state objectives defined above.
  • Analyze transformer internals (attention matrices, residual stream, activation subspaces) to identify structural properties β€” e.g. spectral characteristics, representation collapse, direction vectors linked to specific behaviors β€” that can be exploited or reinforced.
  • Study whether techniques derived on open-weight models (full white-box access) transfer to closed-weight models via black-box/transfer-based optimization, and quantify the transfer gap mathematically.
  • Build a rigorous evaluation methodology: statistically sound metrics, ablations isolating which mathematical property of the input drives the effect, and robustness checks across model families and versions.
  • Assess durability: whether effects derived from current architectures are expected to hold under fine-tuning, distillation, or future model versions, based on the underlying mathematical mechanism rather than empirical trial-and-error.
  • Document the mathematical framework, methods, and results internally for Apple's use only; no external publication.

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.

54 results

  • A
    AppleSoftware Engineering Intern - App Intelligence Experience
    Cambridge, United Kingdom
    Software EngineeringInternship
    2 days ago
  • A
    AppleIntern - Software Development Engineer
    Munich, Germany
    Software EngineeringInternship
    2 days ago
  • A
    AppleSoftware Engineer - AI & Data Platforms
    Hyderabad, India
    Software EngineeringNew Grad
    2 days ago
  • A
    AppleAR/VR Software Engineer - Spatial System UI - Vision Products Software
    Sunnyvale, CA
    Software EngineeringNew Grad
    2 days ago
  • A
    AppleAR/VR Software Engineer - Spatial System UI - Vision Products Software
    Boulder, CO
    Software EngineeringNew Grad
    2 days ago
  • A
    AppleGraduate Systems Software Engineer - File Provider Sync - CoreOS
    Paris, France
    Software EngineeringNew Grad
    3 days ago
  • A
    AppleAIML - LLM Inference Quality Engineer
    Seattle, WA
    AI / MLNew Grad
    3 days ago
  • A
    AppleSoftware Engineering Intern - Full-Stack & AI Integration - Shanghai
    Shanghai, China
    Software EngineeringInternship
    4 days ago
  • A
    AppleSoftware Engineering Intern - Apple Services - Dublin - Ireland
    Dublin, Ireland
    Software EngineeringInternship
    4 days ago
  • A
    AppleSoftware Engineering Intern - File Previewing & Editing - Quick Look and Preview
    Paris, France
    Software EngineeringInternship
    5 days ago
  • A
    AppleJunior Fullstack Engineer - ETS
    Hyderabad, India
    Software EngineeringNew Grad
    5 days ago
  • A
    AppleDefensive AI Security Intern
    Paris, France
    AI / MLInternship
    6 days ago
  • A
    AppleInternship - Pro Apps Machine Learning Ecosystem Engineer
    London, United Kingdom
    AI / MLInternship
    10 days ago
  • A
    AppleCamera Software - Intern
    Cambridge, United Kingdom
    Software EngineeringInternship
    10 days ago
  • A
    AppleInternship - Software Development Intern - Core OS
    Prague, Czechia
    Software EngineeringInternship
    10 days ago
  • A
    AppleMachine Learning Engineering Intern - Personal Agentic Search
    Cambridge, United Kingdom
    AI / MLInternship
    12 days ago
  • A
    AppleVirtualisation Software Engineering Internship - CoreOS
    London, United Kingdom
    Software EngineeringInternship
    12 days ago
  • A
    AppleIntern - Software Automation Engineer
    Cork, Ireland
    Software EngineeringInternship
    16 days ago
  • A
    AppleSoftware Engineer Intern - Full-Stack & AI Agents - Shanghai
    Shanghai, China
    Software EngineeringInternship
    18 days ago
  • A
    AppleSoftware Engineer - VE
    Cupertino, CA
    Software EngineeringNew Grad
    19 days ago
1 / 3Next

Logos provided by Logo.dev