{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OP6TCEI4PW4TO65MHAGKAJ5YL2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"456f5e08530b49a35be497ad427bd2b778adafb0f3a10d5c825150c9850b6456","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T09:56:48Z","title_canon_sha256":"24013bbb337d35c973333dd1200fab8577f1b860814cb8b6094b52f73d86587c"},"schema_version":"1.0","source":{"id":"2606.05958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05958","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05958v1","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05958","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_12","alias_value":"OP6TCEI4PW4T","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_16","alias_value":"OP6TCEI4PW4TO65M","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_8","alias_value":"OP6TCEI4","created_at":"2026-06-05T01:15:28Z"}],"graph_snapshots":[{"event_id":"sha256:594b43b20f3a9fd080175d135a0d30831e464e04b2bcbe3405a6a5a5afc8a6da","target":"graph","created_at":"2026-06-05T01:15:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.05958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning. Since the technique is plug-and-play, users share datasets and precomputed vectors to steer model activations. However, we show that a \\emph{stealth data poisoning attack} silently compromises this pipeline. By substituting $4{-}6\\%$ of tokens in the steering dataset, an attacker can silently align the resulting vector with an anti-refusal direction. This jailbreaks the target model while preserving the intended steering effect on benign prompts. Under this threat model, a malicious","authors_text":"Abzal Aidakhmetov, Adrian Robert Minut, Donato Crisostomi, Emanuele Rodol\\`a, Iacopo Masi, Tommaso Mencattini","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T09:56:48Z","title":"Steering Vectors are an Adversarial Attack Surface"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05958","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6eaac79df069d3bfc304846f49001cd0db3945e1f78d041988d70f1136e8c3bf","target":"record","created_at":"2026-06-05T01:15:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"456f5e08530b49a35be497ad427bd2b778adafb0f3a10d5c825150c9850b6456","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T09:56:48Z","title_canon_sha256":"24013bbb337d35c973333dd1200fab8577f1b860814cb8b6094b52f73d86587c"},"schema_version":"1.0","source":{"id":"2606.05958","kind":"arxiv","version":1}},"canonical_sha256":"73fd31111c7db9377bac380ca027b85eba5c72cd6c8ee3a617f140aded3f7dcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73fd31111c7db9377bac380ca027b85eba5c72cd6c8ee3a617f140aded3f7dcb","first_computed_at":"2026-06-05T01:15:28.795125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:28.795125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lMwf3sWxCwRfp4kuE72NG9jU5bwc1PNLKnBKuD9/52Pq7FJvIYMQlpRVCwuyofS+IqprT7BAVqMocyn01GqtAw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:28.795581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eaac79df069d3bfc304846f49001cd0db3945e1f78d041988d70f1136e8c3bf","sha256:594b43b20f3a9fd080175d135a0d30831e464e04b2bcbe3405a6a5a5afc8a6da"],"state_sha256":"24a795b7048a0c51b587edede97a53741b688226720fedc5166c3eeab1fc87a8"}