{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4IOU7DUOOR2FSEEDNKMTI5GLEP","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":"cc8e7ef0150925a2b27aca6982afd6c82e4a033319b5f920ffaa7bebd8319dff","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T21:25:58Z","title_canon_sha256":"451301b5fae42729d876b81f0e212443076b866b516a47782b3d7793ce861e18"},"schema_version":"1.0","source":{"id":"2411.05189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05189","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05189v2","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05189","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"pith_short_12","alias_value":"4IOU7DUOOR2F","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"pith_short_16","alias_value":"4IOU7DUOOR2FSEED","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"pith_short_8","alias_value":"4IOU7DUO","created_at":"2026-07-05T11:49:05Z"}],"graph_snapshots":[{"event_id":"sha256:66a4723aa10f7a06d60ddd5772803d9ca067f87c1a785f098fe4a1944bb6913a","target":"graph","created_at":"2026-07-05T11:49:05Z","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/2411.05189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-context learning in transformers to hijacking attacks -- a type of adversarial attacks in which the adversary's goal is to manipulate the prompt to force the transformer to generate a specific output. We show that both linear transformers and transformers with GPT-2 architectures are vulnerable to such hijacking attacks. However, adversarial robustness to such attacks can be significantly improved through adversarial train","authors_text":"David Krueger, Johannes von Oswald, Louis Kirsch, Spencer Frei, Usman Anwar","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T21:25:58Z","title":"Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05189","kind":"arxiv","version":2},"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":"sha256:41a01be4fb221d9b2caefe7c936bacc91c36197a550398c8131b8805e15225de","target":"record","created_at":"2026-07-05T11:49:05Z","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":"cc8e7ef0150925a2b27aca6982afd6c82e4a033319b5f920ffaa7bebd8319dff","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T21:25:58Z","title_canon_sha256":"451301b5fae42729d876b81f0e212443076b866b516a47782b3d7793ce861e18"},"schema_version":"1.0","source":{"id":"2411.05189","kind":"arxiv","version":2}},"canonical_sha256":"e21d4f8e8e74745910836a993474cb23c4a347b5947d9c176223f8d495587ba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e21d4f8e8e74745910836a993474cb23c4a347b5947d9c176223f8d495587ba8","first_computed_at":"2026-07-05T11:49:05.186800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:05.186800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qKlGSu746BahTRc3mz0yecLpEKEjzUC4pcVLde0M/F2/1kVDD3IesWK6EkCi2fpWZyYw+eoPlyhJJODd5+6oCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:05.187233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41a01be4fb221d9b2caefe7c936bacc91c36197a550398c8131b8805e15225de","sha256:66a4723aa10f7a06d60ddd5772803d9ca067f87c1a785f098fe4a1944bb6913a"],"state_sha256":"c2c030348655e824dea8f398368e09c9223ec636f24b0c335bce57380e9f322d"}