Speaker

Adam Smith

Adam Smith

Washington, District of Columbia, United States

Actions

Area of Expertise

  • Information & Communications Technology

Topics

  • DevOps
  • cybersecurity
  • DevSecOps
  • Cloud Native
  • Cloud Security
  • Kubernetes
  • kubecon
  • Container and Kubernetes security
  • AI and Cybersecurity
  • Rust
  • Zero-Trust Security
  • zero trust
  • rustlang
  • Rust Programming Language
  • Rust Development
  • Rust Community
  • Smart Contracts with Rust
  • web3
  • Web3.0
  • blockchain
  • Dapps
  • Decentralization
  • Decentralized Web
  • Decentralized Systems
  • decentralized identity
  • decentralized governance
  • Kubernetes Security
  • Cloud Native & Kubernetes
  • aws
  • Azure
  • Azure AD
  • OIDC
  • OAuth
  • OAuth2
  • golang
  • GCP
  • cyber security
  • Emerging Cybersecurity Topics
  • Artificial Intelligence and Machine Learning for Cybersecurity
  • Active Cyber Defence
  • Makerspaces
  • cubesats
  • Data Security
  • Data Engineering
  • AI Data Engineering
  • Data Privacy
  • Data Warehousing
  • Data Governance
  • Data Science & AI
  • Data Engineering Pipelines
  • Data extraction and ingest
  • Data Driven Organisations
  • Data Architecture
  • Big Data Machine Learning AI and Analytics
  • Fabric Data Engineering
  • Information Retrieval and Data Engineering in Government Systems
  • Voting
  • Voter Registration
  • Robotics and Drone Technologies
  • Drones
  • drone technology
  • drone mapping
  • Unmanned Aerial Vehicle
  • Offensive Security
  • Hacking
  • Hackathon
  • Hackathons
  • Car Hacking
  • API Hacks
  • RF hacking
  • SCADA Hacking
  • hardware hacking
  • DeFi protocol hacks are on the rise - How can companies protect themselves?
  • owasp
  • OWASP
  • isc2
  • riscv
  • Knowledge Discovery
  • Continuous Discovery
  • BSides
  • BSides CDMX
  • cybercrime
  • Cyberthreats
  • Women in Cyber
  • cyber forensics
  • Cyber Security basics
  • Cybersecurity Threats and Trends
  • Cybersecuirty
  • Cybersecurity Workforce Development and Training

Aether Keys : An Intro to Backdoors in Language Models

At this point, we have all heard of at least one language model, like ChatGPT. Fundamentally, they enable users to store words as numbers & compare those numbers in a novel way to form expert level responses to a user's query about very complex data sets. While a welcome addition to most people's workflow, it is quickly becoming apparent how very little the average user understands the risks that accompany its use.

Only in the past 2 years has research into model focused attacks begun to emerge. In that time, most research assumes a very deep understanding on the reader's part, while little has been done to describe the state of the field in general.

So, how are you supposed to know how to evaluate a model's risk, understand model attack paths, or detect a trojanized model? This talk aims to answer all of those questions, by giving a description of the state of language model security, & provide a model of exploitation tactics, techniques, & tools.

Adam Smith

Washington, District of Columbia, United States

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top