Stephen Casper
7 papers · 2020–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze
🧬
Topic Evolution
❓
The Questioner
(2)
Venues
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI · Artificial Intelligence
(6)
Machine Learning
(5)
Deep Learning
(3)
Natural Language Processing
(2)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Computer Vision
(1)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Core AI · Computer Vision
(1)
Models
(1)
Keywords
neural network
(3)
adversarial attack
(3)
representation learning
(3)
model debugging
(2)
model safety
(1)
probing analysis
(1)
latent representation
(1)
deep neural network
(1)
implicit regularization
(1)
language model
(1)
out-of-distribution detection
(1)
jailbreak attack
(1)
red teaming
(1)
feature probing
(1)
model diagnosis
(1)
network width
(1)
few-shot prompting
(1)
internal representation
(1)
dialog system
(1)
open-domain dialog
(1)
Papers
STACK: Adversarial Attacks on LLM Safeguard Pipelines
AAAI 2026
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
EMNLP 2025
Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?
EMNLP 2023
Red Teaming Deep Neural Networks with Feature Synthesis Tools
NeurIPS 2023
Robust Feature-Level Adversaries are Interpretability Tools
NeurIPS 2022
Frivolous Units: Wider Networks Are Not Really That Wide
AAAI 2021
Probing Neural Dialog Models for Conversational Understanding
ACL 2020