Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
Paper
•
2503.06269
•
Published
•
4
Thomas Winninger
Sckathach
·
AI & ML interests
Graphs
Recent Activity
upvoted
a
paper
about 1 month ago
Using Mechanistic Interpretability to Craft Adversarial Attacks against
Large Language Models
commented on
a paper
about 1 month ago
Using Mechanistic Interpretability to Craft Adversarial Attacks against
Large Language Models
updated
a dataset
about 1 month ago
Sckathach/ssr-llama3.2-1b-filtered
Organizations
Sckathach's activity
upvoted
a
paper
about 1 month ago
commented
a
paper
about 1 month ago
updated
9
datasets
about 1 month ago
Sckathach/ssr-llama3.2-1b-filtered
Viewer
•
Updated
•
37
•
34
Sckathach/ssr-gemma2-2b-filtered
Viewer
•
Updated
•
48
•
28
Sckathach/ssr-steering-gemma2-2b-filtered
Viewer
•
Updated
•
29
•
40
Sckathach/ssr-steering-llama3.2-1b-filtered
Viewer
•
Updated
•
46
•
33
Sckathach/ssr-steering-llama3.2-3b-filtered
Viewer
•
Updated
•
22
•
30
Sckathach/ssr-steering-qwen2.5-1.5b-filtered
Viewer
•
Updated
•
53
•
34
Sckathach/ssr-probes-llama3.2-1b-short
Viewer
•
Updated
•
532
•
31
Sckathach/ssr-steering-llama3.2-1b-short
Viewer
•
Updated
•
140
•
31
Sckathach/ssr-probes-qwen2.5-1.5b-short
Viewer
•
Updated
•
244
•
30
authored
a
paper
about 1 month ago
published
8
datasets
about 1 month ago
Sckathach/ssr-probes-qwen2.5-1.5b-short
Viewer
•
Updated
•
244
•
30
Sckathach/ssr-steering-llama3.2-1b-short
Viewer
•
Updated
•
140
•
31
Sckathach/ssr-probes-llama3.2-1b-short
Viewer
•
Updated
•
532
•
31
Sckathach/ssr-steering-qwen2.5-1.5b-filtered
Viewer
•
Updated
•
53
•
34
Sckathach/ssr-steering-llama3.2-3b-filtered
Viewer
•
Updated
•
22
•
30
Sckathach/ssr-steering-llama3.2-1b-filtered
Viewer
•
Updated
•
46
•
33
Sckathach/ssr-steering-gemma2-2b-filtered
Viewer
•
Updated
•
29
•
40
Sckathach/ssr-gemma2-2b-filtered
Viewer
•
Updated
•
48
•
28