The DOI matches its Crossref record.
did i say something wrong?': Towards a safe collaborative chatbot
Open accessAbstract
Chatbots have been a core measure of AI since Turing has presented his test for intelligence, and are also widely used for entertainment purposes. In this paper we present a platform that enables users to collaboratively teach a chatbot responses, using natural language. We present a method of collectively detecting malicious users and using the commands taught by these users to further mitigate activity of future malicious users.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Enterprises like Apple have used differential privacy to transform user data into a form from which the true data cannot be reproduced.
“Enterprises like Apple have used DP to transform user data into a form from which the true data cannot be reproduced [20].”
From Trustworthy AI: From Principles to Practices (2023) · cites this paper as [20]
The Safebot section (p. 1) describes detecting malicious chatbot responses, not protecting user data through differential privacy. Searches for Apple, differential privacy, and reconstruction of user data found no passage addressing the claim. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 9
- Azaria, A.; Krishnamurthy, J.; and Mitchell, T. M. 2016. Instructable intelligent personal agent. In AAAI .
- Giles, J. 2005. Wisdom of the crowd. Nature 438(7066):281.
- Huang, T.-H. K.; Azaria, A.; and Bigham, J. P. 2016. Instructablecrowd: Creating if-then rules via conversations with the crowd. In CHI (Extended Abstracts) , 1555-1562. ACM.
- Huang, J.; Zhou, M.; and Yang, D. 2007. Extracting chatbot knowledge from online discussion forums. In IJCAI .
- Mauldin, M. L. 1994. Chatterbots, tinymuds, and the turing test: Entering the loebner prize competition. In AAAI , volume 94, 16-21.
- Neff, G., and Nagy, P. 2016. Automation, algorithms, and politics- talking to bots: Symbiotic agency and the case of tay. International Journal of Communication 10:17.
- Spierling, U. 2008. killer phrases: Design steps for a game with digital role-playing agents. Transactions on edutainment I 150-161.
- Subrahmanian, V.; Azaria, A.; Durst, S.; Kagan, V.; Galstyan, A.; Lerman, K.; Zhu, L.; Ferrara, E.; Flammini, A.; and Menczer, F. 2016. The darpa twitter bot challenge. Computer 49(6):38-46.
- Weizenbaum, J. 1966. Elizaa computer program for the study of natural language communication between man and machine. Communications of the ACM 9(1):36-45.
Cited by
Sorted by citations
Trustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612
Metadata
- Authors
- Chkroun, M., & Azaria, A.
- Affiliations
- Ariel University (IL)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2018-04-29
- Volume
- 32
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2806131067
- Cited by
- 6
- References
- 0
- Citations by year
- 2023: 1 · 2022: 1 · 2020: 1 · 2019: 2 · 2018: 1
- FWCI
- 0.78
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- Funders
- Samsung
- Topics
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- chatbot safety, malicious user detection, natural language instructions, cooperative learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
