SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.10601 · NeurIPS · 2024

When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Ciphers

Chitta Baral, Divij Handa, Zehua Zhang, Amir Saeidi, Shrinidhi Kumbhar, Nayem Uddin, Aswin Rrv, Plain English

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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 1 has no contract verdict; 0 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/2402.10601.json · badge: /api/ran/2402.10601.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
divijh/jailbreak_cryptography canonical (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
FunctionStatusWhere it lives
EncodeDataset Ran
ran on a synthesized input
divijh/jailbreak_cryptography/src/data_gen/substitution+grid.py
pointer only (licence: NONE) · get_code("42d766099158d34e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, divijh/jailbreak_cryptography 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.

GridEncoding Not yet run
unverified (harvested, no recorded run)
divijh/jailbreak_cryptography/src/data_gen/substitution+grid.py
pointer only (licence: NONE) · get_code("4655af0f49c1f058")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, divijh/jailbreak_cryptography 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.

Substitution_Grid Not yet run
unverified (harvested, no recorded run)
divijh/jailbreak_cryptography/src/data_gen/substitution+grid.py
pointer only (licence: NONE) · get_code("36f082eb430585e2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, divijh/jailbreak_cryptography 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.

WordSubstitution Not yet run
unverified (harvested, no recorded run)
divijh/jailbreak_cryptography/src/data_gen/substitution+grid.py
pointer only (licence: NONE) · get_code("e45e872f8a9ed952")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, divijh/jailbreak_cryptography 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g., Base64), which are likely integrated into newer models' safety training. However, we reveal a paradoxical vulnerability: as LLMs advance in reasoning, they inadvertently become more susceptible to novel jailbreaking attacks. Enhanced reasoning enables LLMs to interpret complex instructions and decode complex userdefined ciphers, creating an exploitable security gap. To study this vulnerability, we introduce Attacks using Custom Encryptions (ACE), a jailbreaking technique that encodes malicious queries with novel ciphers. Extending ACE, we introduce Layered Attacks using Custom Encryptions (LACE), which applies multi-layer ciphers to amplify attack complexity. Furthermore, we develop CipherBench, a benchmark designed to evaluate LLMs' accuracy in decoding encrypted benign text. Our experiments reveal a critical trade-off: LLMs that are more capable of decoding ciphers are more vulnerable to LACE, with success rates on gpt-oss-20b escalating from 60% under ACE to 72% with LACE. These findings highlight a critical insight: as LLMs become more adept at deciphering complex user ciphersmany of which cannot be preemptively included in safety training-they become increasingly exploitable. 1 Content Warning: This paper contains possibly offensive content generated by LLMs.

For agents

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

get_harvested_code_for_paper("2402.10601")
get_code_for_paper("2402.10601")
have("2402.10601")

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

curl https://syntology.ai/api/ran/2402.10601.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.10601.svg)](https://syntology.ai/paper/2402.10601)

Connect an agent — have() is free.