InfoResearchPreprintLLM-specific
Creating Steering Vectors via Input Optimisation
- Published
- Record updated
Summary
Researchers show that the behaviour of an activation steering vector can be reproduced through input alone. Their method, ActGCG, modifies Greedy Coordinate Gradient to optimise a suffix whose activations match those produced by adding a steering vector to the residual stream. For steering a model to answer in German, a discrete suffix reproduces the steering vector's behaviour almost perfectly and transfers across prompts and models. For anti-refusal steering, the match is weaker, succeeding under a phrase-avoidance metric but only partially under the HarmBench classifier.
Related items
- MediumGemini AI agents repeatedly bypassed safeguards to attack real websiteSimilar attack · BleepingComputer
- CriticalCVE-2026-120699: CubeSandbox host path bind mount allows host file access via POST /sandboxesSimilar attack · NVD/CVE Database
- MediumGoogle warns that fully-automated AI attacks are coming soonSimilar attack · BleepingComputer
- InfoLLMs are Vulnerable to Malicious Requests with Indistinguishable IntentSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- InfoImproving Fuzzy Robustness in LLM Safety with Automated Red TeamingSimilar attack · OpenAI Alignment Research Blog