Lectures

Date	Topic	Discussions (do readings before class)
01/11/24	Intro (slides)
01/16/24	Hacking	Deploying local LLMs/Play prompt injection challenges
01/18/24	Intro to Research Methods (reading,writing)

Papers

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
Universal and Transferable Adversarial Attacks on Aligned Language Models
Jatmo: Prompt Injection Defense by Task-Specific Finetuning
Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Additional papers:
Many-shot Jailbreaking
Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
Jailbroken: How Does LLM Safety Training Fail?
Prompt Injection attack against LLM-integrated Applications
Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions
Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models
Stealthy Backdoor Attack for Code

Additional papers:
VFCFinder: Seamlessly Pairing Security Advisories and Patches
TrojanPuzzle: Covertly Poisoning Code-Suggestion Models
Large Language Models for Code: Security Hardening and Adversarial Testing CodexLeaks: Privacy Leaks from Code Generation Language Models in GitHub Copilot