SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.09433 · 2023

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2311.09433.json · badge: /api/ran/2311.09433.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
wang2226/backdoor-activation-attack canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
assemble_prompt Ran
ran; our contract draft was wrong, not the code
wang2226/backdoor-activation-attack/evaluate_tqa.py
pointer only (licence: NONE) · get_code("d218185247c774ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wang2226/backdoor-activation-attack when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

eval_truth Ran
ran; our contract draft was wrong, not the code
wang2226/backdoor-activation-attack/evaluate_tqa.py
pointer only (licence: NONE) · get_code("5029f3c09f9e8145")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wang2226/backdoor-activation-attack when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

process_output Ran
ran; our contract draft was wrong, not the code
wang2226/backdoor-activation-attack/evaluate_tqa.py
pointer only (licence: NONE) · get_code("6a96f97f2ea067bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wang2226/backdoor-activation-attack when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gen Not yet run
unverified (harvested, no recorded run)
wang2226/backdoor-activation-attack/clean_run.py
pointer only (licence: NONE) · get_code("01e01256ca25545a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wang2226/backdoor-activation-attack when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

genearte_results Not yet run
unverified (harvested, no recorded run)
wang2226/backdoor-activation-attack/attack.py
pointer only (licence: NONE) · get_code("1f34b65cb2d27bf9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wang2226/backdoor-activation-attack when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

generate_and_save_steering_vectors Not yet run
unverified (harvested, no recorded run)
wang2226/backdoor-activation-attack/attack.py
pointer only (licence: NONE) · get_code("e5adf30f20ad4a79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wang2226/backdoor-activation-attack when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

To ensure AI safety, instruction-tuned Large Language Models (LLMs) are specifically trained to ensure alignment, which refers to making models behave in accordance with human intentions. While these models have demonstrated commendable results on various safety benchmarks, the vulnerability of their safety alignment has not been extensively studied. This is particularly troubling given the potential harm that LLMs can inflict. Existing attack methods on LLMs often rely on poisoned training data or the injection of malicious prompts. These approaches compromise the stealthiness and generalizability of the attacks, making them susceptible to detection. Additionally, these models often demand substantial computational resources for implementation, making them less practical for real-world applications. In this work, we study a different attack scenario, called Trojan Activation Attack (TA^2), which injects trojan steering vectors into the activation layers of LLMs. These malicious steering vectors can be triggered at inference time to steer the models toward attacker-desired behaviors by manipulating their activations. Our experiment results on four primary alignment tasks show that TA^2 is highly effective and adds little or no overhead to attack efficiency. Additionally, we discuss potential countermeasures against such activation attacks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2311.09433")
get_code_for_paper("2311.09433")
have("2311.09433")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2311.09433.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2311.09433.svg)](https://syntology.ai/paper/2311.09433)

Connect an agent — have() is free.