AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Causes and Consequences of Representational Similarity in Machine Learning Models

Zeyu Michael Li, Hung Anh Vu, Damilola Awofisayo, Emily Wenger

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial prompts for language models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase dataset overlap between two training sets (ablation)finetuned ResNet/ViT image classifiers · TinyImageNetCKA between model pairs: ResNet18 R2=0.99, y=0.02x+0.95; ViT/small R2=0.98Improved
increase dataset overlap between two training sets (ablation)ResNet101 · TinyImageNetCKA between model pairs: R2=0.24No clear effect
increase dataset overlap between two training sets (ablation)Llama-3.2-Instruct LoRA CPT · Tiny-CodesCKA between model pairs: R2=0.01 (1B), 0.03 (3B), 0.02 (11B)No clear effect
increase task and dataset overlap together (ablation)ResNet/ViT classifiers · TinyImageNetCKA between model pairs: ResNet18 R2=0.92; ViT/tiny R2=0.86Improved
increase task and dataset overlap together (ablation)Llama LoRA CPT · CPT corporaCKA between model pairs: R2=0.62 (1B), 0.47 (3B), 0.54 (11B)Mixed
increase task overlap with data overlap held at 100% via relabeling (ablation)ResNet/ViT · ColorShapeDigit800KCKA between model pairs: ViT/tiny R2=0.84; ResNet18 R2=0.83Improved
increase label-set task overlap (0%, 50%, 100%) (ablation)XLM-RoBERTa-base · Multilingual Amazon Reviewsrepresentational similarityImproved
compare overlap type by mutual information with similarity (ablation)model families · CKA/CKNNAmutual information: ResNet dataset 1.303 vs task+dataset 0.734; nanoGPT 0.198 vs 1.052Mixed
increase dataset/task overlap between model pairs (ablation)ViT classifiers, MI-FGSM transfer attack · TinyImageNettransfer attack success rate: ViT/tiny R2=0.83, y=0.20x+0.57Improved
increase dataset/task overlap between LLM pairs (ablation)Llama 3.2 continued-pretrained models · jailbreak transfer, Llama-70B judgetransfer jailbreak ASR: R2=0.01, 0.00, 0.04No clear effect
train longer on LLM continued pretraining to test insufficient adaptation (ablation)Llama CPT and instruction finetuning · perplexity across overlap settingsperplexityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy