Tampering with Generative Artificial Intelligence by Jailbreaking

被引:0
|
作者
Claverini, Corrado [1 ]
机构
[1] Univ Salento, Lecce, Italy
来源
TEORIA-RIVISTA DI FILOSOFIA | 2024年 / 44卷 / 01期
关键词
ChatGPT; ethics of artificial intelligence; generative artificial in- telligence; jailbreaking; regulation of artificial intelligence;
D O I
10.4454/mg6wax06
中图分类号
B [哲学、宗教];
学科分类号
01 ; 0101 ;
摘要
In this paper, I will analyse the risks linked to the use of generative artificial intelligence systems and relative risk-reduction strategies, while concentrating in particular on the possibility of tampering with the chatbot ChatGPT by jailbreaking. After examining how a user can tamper with this generative AI, bypassing its ethical and legal restrictions, through a series of prompts, I will turn my focus to the ethical issues raised by the malicious use of this technology: are the transparency requirements requested of generative AI sufficient or should there be tighter restrictions that do not hinder the innovation and development of these technologies? How can the risk of tampering with these AI tools be lowered? And, should a breach take place, who is responsible: the AI developer or the jailbreaker? To what extent could the changes needed to prevent jailbreaking involuntarily generate or strengthen certain biases? In conclusion, I will uphold the necessity of ethical reflection for the sustainable and "human-centric" development of AI.
引用
收藏
页数:172
相关论文
共 50 条
  • [31] Generative artificial intelligence integrations and applications
    Gilreath, Hanna
    JOURNAL OF PRINT AND MEDIA TECHNOLOGY RESEARCH, 2024, 13 (01): : 35 - 42
  • [32] Generative Artificial Intelligence in Health Care
    Cacciamani, Giovanni E.
    Siemens, D. Robert
    Gill, Inderbir
    JOURNAL OF UROLOGY, 2023, 210 (05): : 723 - 725
  • [33] Generative Artificial Intelligence in Surgical Publishing
    Li, Ben
    Kayssi, Ahmed
    Mclean, Lianne J.
    JAMA SURGERY, 2025,
  • [34] Generative artificial intelligence in smart manufacturing
    Kusiak, Andrew
    JOURNAL OF INTELLIGENT MANUFACTURING, 2025, 36 (01) : 1 - 3
  • [35] Generative artificial intelligence in ophthalmology: Correspondence
    Daungsupawong, Hinpetch
    Wiwanitkit, Viroj
    SURVEY OF OPHTHALMOLOGY, 2024, 69 (05) : 848 - 848
  • [36] Generative artificial intelligence in the metaverse era
    Lv Z.
    Cognitive Robotics, 2023, 3 : 208 - 217
  • [37] SneakyPrompt: Jailbreaking Text-to-image Generative Models
    Yang, Yuchen
    Hui, Bo
    Yuan, Haolin
    Gong, Neil
    Cao, Yinzhi
    45TH IEEE SYMPOSIUM ON SECURITY AND PRIVACY, SP 2024, 2024, : 897 - 912
  • [38] AI and Case Management: From Artificial Intelligence to Generative Intelligence
    Powell, Suzanne K.
    PROFESSIONAL CASE MANAGEMENT, 2023, 28 (06) : 259 - 261
  • [39] Generative artificial intelligence: synthetic datasets in dentistry
    Fahad Umer
    Niha Adnan
    BDJ Open, 10
  • [40] Generative Artificial Intelligence in the Financial Services Industry
    Kshetri, Nir
    COMPUTER, 2024, 57 (06) : 102 - 108