Built on

J. Kelsey, B. Schneier, D. A. Wagner, and C. Hall, “Cryptanalytic attacks on pseudorandom number generators,” in Fast Software Encryption Workshop , 1998. [Online]. Available: https://api.semanticscholar.org/CorpusID:14099653
1998
Earlier work this paper cites.
K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “Bleu: a method for automatic evaluation of machine translation,” in Annual Meeting of the Association for Computational Linguistics , 2002. [Online]. Available: https://api.semanticscholar.org/CorpusID:11080756
2002
Earlier work this paper cites.
T. Gu, B. Dolan-Gavitt, and S. Garg, “Badnets: Identifying vulnerabilities in the machine learning model supply chain,” ArXiv , vol. abs/1708.06733, 2017. [Online]. Available: https://api.semanticscholar.org/CorpusID:26783139
Original
2017
Earlier work this paper cites.
T. Gu, B. Dolan-Gavitt, and S. Garg, “Badnets: Identifying vulnerabilities in the machine learning model supply chain,” ArXiv , 2017
2017
Earlier work this paper cites.
W. Ling, D. Yogatama, C. Dyer, and P. Blunsom, “Program induction by rationale generation: Learning to solve and explain algebraic word problems,” in Annual Meeting of the Association for Computational Linguistics , 2017. [Online]. Available: https://api.semanticscholar.org/CorpusID:12777818
2017
Earlier work this paper cites.
A. Turner, D. Tsipras, and A. Madry, “Clean-label backdoor attacks,” 2018. [Online]. Available: https://api.semanticscholar.org/CorpusID:53636567
2018
Earlier work this paper cites.
A. Talmor, J. Herzig, N. Lourie, and J. Berant, “Commonsenseqa: A question answering challenge targeting commonsense knowledge,” ArXiv , vol. abs/1811.00937, 2019. [Online]. Available: https://api.semanticscholar.org/CorpusID:53296520
Original
2019
Earlier work this paper cites.
T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al. , “Language models are few-shot learners,” Advances in neural information processing systems , vol. 33, pp. 1877–1901, 2020
2020
Earlier work this paper cites.
A. Salem, R. Wen, M. Backes, S. Ma, and Y. Zhang, “Dynamic backdoor attacks against machine learning models,” 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P) , pp. 703–718, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:212633480
2020
Earlier work this paper cites.
S.-Y. Miao, C.-C. Liang, and K.-Y. Su, “A diverse corpus for evaluating and developing english math word problem solvers,” in Annual Meeting of the Association for Computational Linguistics , 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:220047831
2020
Earlier work this paper cites.
M. Weber, X. Xu, B. Karlas, C. Zhang, and B. Li, “Rab: Provable robustness against backdoor attacks,” 2023 IEEE Symposium on Security and Privacy (SP) , pp. 1311–1328, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:213183269
2020
Earlier work this paper cites.
E. Bagdasaryan and V. Shmatikov, “Blind backdoors in deep learning models,” 30th USENIX Security Symposium (USENIX Security 21) , pp. 1505–1521, 2021
2021
Earlier work this paper cites.
K. Cobbe, V. Kosaraju, M. Bavarian, M. Chen, H. Jun, L. Kaiser, M. Plappert, J. Tworek, J. Hilton, R. Nakano, C. Hesse, and J. Schulman, “Training verifiers to solve math word problems,” ArXiv , vol. abs/2110.14168, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:239998651
Original
2021
Earlier work this paper cites.
D. Hendrycks, C. Burns, S. Kadavath, A. Arora, S. Basart, E. Tang, D. X. Song, and J. Steinhardt, “Measuring mathematical problem solving with the math dataset,” ArXiv , vol. abs/2103.03874, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:232134851
Original
2021
Earlier work this paper cites.
A. Patel, S. Bhattamishra, and N. Goyal, “Are nlp models really able to solve simple math word problems?” in North American Chapter of the Association for Computational Linguistics , 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:232223322
2021
Earlier work this paper cites.
M. Geva, D. Khashabi, E. Segal, T. Khot, D. Roth, and J. Berant, “Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies,” Transactions of the Association for Computational Linguistics , vol. 9, pp. 346–361, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:230799347
2021
Earlier work this paper cites.
M. Chen, J. Tworek, H. Jun, Q. Yuan, H. P. de Oliveira Pinto, J. Kaplan, H. Edwards, Y. Burda, N. Joseph, G. Brockman et al. , “Evaluating large language models trained on code,” 2021. [Online]. Available: https://github.com/openai/human-eval
2021
Earlier work this paper cites.

Similar

J. Austin, A. Odena, M. Nye, M. Bosma, H. Michalewski, D. Dohan, E. Jiang, C. Cai, M. Terry, Q. Le, and C. Sutton, “Program synthesis with large language models,” in ICLR , 2021. [Online]. Available: https://github.com/google-research/google-research/tree/master/mbpp
2021
Cited alongside, same era.
T. Kojima, S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa, “Large language models are zero-shot reasoners,” ArXiv , vol. abs/2205.11916, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:249017743
Original
2022
Cited alongside, same era.
H. Trivedi, N. Balasubramanian, T. Khot, and A. Sabharwal, “Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions,” ArXiv , vol. abs/2212.10509, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:254877499
Original
2022
Cited alongside, same era.
B. Wang, S. Min, X. Deng, J. Shen, Y. Wu, L. Zettlemoyer, and H. Sun, “Towards understanding chain-of-thought prompting: An empirical study of what matters,” in Annual Meeting of the Association for Computational Linguistics , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:254877569

Then

N. Kandpal, M. Jagielski, F. Tramèr, and N. Carlini, “Backdoor attacks for in-context learning with language models,” ArXiv , vol. abs/2307.14692, 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:260203047
Original
2023
Later among the works it cites.
Z. Xiang, Z. Xiong, and B. Li, “Umd: Unsupervised model detection for x2x backdoor attacks,” in International Conference on Machine Learning , 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:258967978
2023
Later among the works it cites.
Originality.ai, “Gpts statistics: Insights from the gpt store,” 2024, accessed: 2024-10-26. [Online]. Available: https://originality.ai/blog/gpts-statistics
2024
Later among the works it cites.
R. Zhang, H. Li, R. Wen, W. Jiang, Y. Zhang, M. Backes, Y. Shen, and Y. Zhang, “Instruction backdoor attacks against customized llms,” in USENIX Security Symposium , 2024. [Online]. Available: https://api.semanticscholar.org/CorpusID:267657775
2024
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2025

DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs

Guo, Zhen, Shi, Shanghao, Yazdani, Shamim et al.

Understand

With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents.

However, their complex reasoning processes introduce new and largely unexplored security vulnerabilities.
We present DarkMind, a novel latent reasoning level backdoor attack that targets customized LLMs by manipulating internal COT steps without altering user queries.
Unlike prior prompt based attacks, DarkMind activates covertly within the reasoning chain via latent triggers, enabling adversarial behaviors without modifying input prompts or requiring access to model parameters.

Built on

J. Kelsey, B. Schneier, D. A. Wagner, and C. Hall, “Cryptanalytic attacks on pseudorandom number generators,” in Fast Software Encryption Workshop , 1998. [Online]. Available: https://api.semanticscholar.org/CorpusID:14099653
1998
Earlier work this paper cites.
K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “Bleu: a method for automatic evaluation of machine translation,” in Annual Meeting of the Association for Computational Linguistics , 2002. [Online]. Available: https://api.semanticscholar.org/CorpusID:11080756
2002
Earlier work this paper cites.
T. Gu, B. Dolan-Gavitt, and S. Garg, “Badnets: Identifying vulnerabilities in the machine learning model supply chain,” ArXiv , vol. abs/1708.06733, 2017. [Online]. Available: https://api.semanticscholar.org/CorpusID:26783139
Original
2017
Earlier work this paper cites.
T. Gu, B. Dolan-Gavitt, and S. Garg, “Badnets: Identifying vulnerabilities in the machine learning model supply chain,” ArXiv , 2017
2017
Earlier work this paper cites.
W. Ling, D. Yogatama, C. Dyer, and P. Blunsom, “Program induction by rationale generation: Learning to solve and explain algebraic word problems,” in Annual Meeting of the Association for Computational Linguistics , 2017. [Online]. Available: https://api.semanticscholar.org/CorpusID:12777818
2017
Earlier work this paper cites.
A. Turner, D. Tsipras, and A. Madry, “Clean-label backdoor attacks,” 2018. [Online]. Available: https://api.semanticscholar.org/CorpusID:53636567
2018
Earlier work this paper cites.
A. Talmor, J. Herzig, N. Lourie, and J. Berant, “Commonsenseqa: A question answering challenge targeting commonsense knowledge,” ArXiv , vol. abs/1811.00937, 2019. [Online]. Available: https://api.semanticscholar.org/CorpusID:53296520
Original
2019
Earlier work this paper cites.
T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al. , “Language models are few-shot learners,” Advances in neural information processing systems , vol. 33, pp. 1877–1901, 2020
2020
Earlier work this paper cites.
A. Salem, R. Wen, M. Backes, S. Ma, and Y. Zhang, “Dynamic backdoor attacks against machine learning models,” 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P) , pp. 703–718, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:212633480
2020
Earlier work this paper cites.
S.-Y. Miao, C.-C. Liang, and K.-Y. Su, “A diverse corpus for evaluating and developing english math word problem solvers,” in Annual Meeting of the Association for Computational Linguistics , 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:220047831
2020
Earlier work this paper cites.
M. Weber, X. Xu, B. Karlas, C. Zhang, and B. Li, “Rab: Provable robustness against backdoor attacks,” 2023 IEEE Symposium on Security and Privacy (SP) , pp. 1311–1328, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:213183269
2020
Earlier work this paper cites.
E. Bagdasaryan and V. Shmatikov, “Blind backdoors in deep learning models,” 30th USENIX Security Symposium (USENIX Security 21) , pp. 1505–1521, 2021
2021
Earlier work this paper cites.
K. Cobbe, V. Kosaraju, M. Bavarian, M. Chen, H. Jun, L. Kaiser, M. Plappert, J. Tworek, J. Hilton, R. Nakano, C. Hesse, and J. Schulman, “Training verifiers to solve math word problems,” ArXiv , vol. abs/2110.14168, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:239998651
Original
2021
Earlier work this paper cites.
D. Hendrycks, C. Burns, S. Kadavath, A. Arora, S. Basart, E. Tang, D. X. Song, and J. Steinhardt, “Measuring mathematical problem solving with the math dataset,” ArXiv , vol. abs/2103.03874, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:232134851
Original
2021
Earlier work this paper cites.
A. Patel, S. Bhattamishra, and N. Goyal, “Are nlp models really able to solve simple math word problems?” in North American Chapter of the Association for Computational Linguistics , 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:232223322
2021
Earlier work this paper cites.
M. Geva, D. Khashabi, E. Segal, T. Khot, D. Roth, and J. Berant, “Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies,” Transactions of the Association for Computational Linguistics , vol. 9, pp. 346–361, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:230799347
2021
Earlier work this paper cites.
M. Chen, J. Tworek, H. Jun, Q. Yuan, H. P. de Oliveira Pinto, J. Kaplan, H. Edwards, Y. Burda, N. Joseph, G. Brockman et al. , “Evaluating large language models trained on code,” 2021. [Online]. Available: https://github.com/openai/human-eval
2021
Earlier work this paper cites.

Similar

J. Austin, A. Odena, M. Nye, M. Bosma, H. Michalewski, D. Dohan, E. Jiang, C. Cai, M. Terry, Q. Le, and C. Sutton, “Program synthesis with large language models,” in ICLR , 2021. [Online]. Available: https://github.com/google-research/google-research/tree/master/mbpp
2021
Cited alongside, same era.
T. Kojima, S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa, “Large language models are zero-shot reasoners,” ArXiv , vol. abs/2205.11916, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:249017743
Original
2022
Cited alongside, same era.
H. Trivedi, N. Balasubramanian, T. Khot, and A. Sabharwal, “Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions,” ArXiv , vol. abs/2212.10509, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:254877499
Original
2022
Cited alongside, same era.
B. Wang, S. Min, X. Deng, J. Shen, Y. Wu, L. Zettlemoyer, and H. Sun, “Towards understanding chain-of-thought prompting: An empirical study of what matters,” in Annual Meeting of the Association for Computational Linguistics , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:254877569

Then

N. Kandpal, M. Jagielski, F. Tramèr, and N. Carlini, “Backdoor attacks for in-context learning with language models,” ArXiv , vol. abs/2307.14692, 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:260203047
Original
2023
Later among the works it cites.
Z. Xiang, Z. Xiong, and B. Li, “Umd: Unsupervised model detection for x2x backdoor attacks,” in International Conference on Machine Learning , 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:258967978
2023
Later among the works it cites.
Originality.ai, “Gpts statistics: Insights from the gpt store,” 2024, accessed: 2024-10-26. [Online]. Available: https://originality.ai/blog/gpts-statistics
2024
Later among the works it cites.
R. Zhang, H. Li, R. Wen, W. Jiang, Y. Zhang, M. Backes, Y. Shen, and Y. Zhang, “Instruction backdoor attacks against customized llms,” in USENIX Security Symposium , 2024. [Online]. Available: https://api.semanticscholar.org/CorpusID:267657775
2024
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

2022

Cited alongside, same era.

J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, D. Zhou et al. , “Chain-of-thought prompting elicits reasoning in large language models,” Advances in neural information processing systems , vol. 35, pp. 24 824–24 837, 2022

2022

Cited alongside, same era.

J. Wei, X. Wang, D. Schuurmans, M. Bosma, E. H. hsin Chi, F. Xia, Q. Le, and D. Zhou, “Chain of thought prompting elicits reasoning in large language models,” ArXiv , vol. abs/2201.11903, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:246411621

Original

2022

Cited alongside, same era.

M. Suzgun, N. Scales, N. Scharli, S. Gehrmann, Y. Tay, H. W. Chung, A. Chowdhery, Q. V. Le, E. H. Chi, D. Zhou, and J. Wei, “Challenging big-bench tasks and whether chain-of-thought can solve them,” in Annual Meeting of the Association for Computational Linguistics , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:252917648

2022

Cited alongside, same era.

A. Madaan, S. Zhou, U. Alon, Y. Yang, and G. Neubig, “Language models of code are few-shot commonsense learners,” ArXiv , vol. abs/2210.07128, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:252873120

Original

2022

Cited alongside, same era.

M. Goldblum, L. Fowl, C. Sitawarin, Z. He, G. Taylor, and T. Goldstein, “Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses,” IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022

2022

Cited alongside, same era.

Y. Zeng, M. Pan, H. A. Just, L. Lyu, M. Qiu, and R. Jia, “Narcissus: A practical clean-label backdoor attack with limited information,” Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:248084906

2022

Cited alongside, same era.

X. Cai, H. Xu, S. Xu, Y. Zhang, and X. Yuan, “Badprompt: Backdoor attacks on continuous prompts,” ArXiv , vol. abs/2211.14719, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:254043765

Original

2022

Cited alongside, same era.

B. Wang, C. Xu, X. Liu, Y.-K. Cheng, and B. Li, “Semattack: Natural textual attacks via different semantic spaces,” in NAACL-HLT , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:248453465

2022

Cited alongside, same era.

Z. Xiang, F. Jiang, Z. Xiong, B. Ramasubramanian, R. Poovendran, and B. Li, “Badchain: Backdoor chain-of-thought prompting for large language models,” ArXiv , 2024

2024